© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74637
    Prev
    Next
    INDEX
    Explanations

    code directives and keywords

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

    The neuron fires on numeric constants (integer or floating‐point literals) in source code.

    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
    傒
    -1.73
    いえば
    -1.60
    よくある
    -1.59
    xvii
    -1.56
    März
    -1.52
    辚
    -1.52
    鶿
    -1.45
     raisonnable
    -1.44
    MAXN
    -1.44
     dobry
    -1.41
    POSITIVE LOGITS
     and
    1.69
    ↵↵
    1.69
     尤
    1.42
     because
    1.38
     possesses
    1.36
    Lame
    1.36
     at
    1.32
    Petite
    1.30
     seems
    1.26
    Évaluation
    1.26
    Activations Density 0.036%

    No Known Activations