© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113036
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    hyphens connecting words in technical compound terms or identifiers (especially in code and technical documentation).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on hyphenated tokens, i.e. words or identifiers containing one or more dashes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     about
    -1.46
     meninas
    -1.41
     família
    -1.41
    これも
    -1.40
     palha
    -1.39
    </em>
    -1.39
     apesar
    -1.38
     months
    -1.38
     lápis
    -1.34
     though
    -1.29
    POSITIVE LOGITS
    其他
    1.68
    2
    1.61
    anything
    1.53
     Wartawan
    1.49
     cualquiera
    1.42
    0
    1.42
     These
    1.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.41
    3
    1.41
     themſelves
    1.39
    Activations Density 0.161%

    No Known Activations