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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79925
    Prev
    Next
    INDEX
    Explanations

    health and science citations

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

    technical or academic terms within specialized contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on salient technical or domain‐specific key nouns (e.g. specialized jargon and topic words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    },'
    -0.93
    ஈ
    -0.92
    How
    -0.92
    مرح
    -0.92
    adla
    -0.90
    ashley
    -0.87
    isseur
    -0.87
    ஐ
    -0.86
     ninguno
    -0.85
     cukru
    -0.85
    POSITIVE LOGITS
     itself
    1.07
    ol
    0.89
    ole
    0.86
    en
    0.84
     ایر
    0.81
    and
    0.79
    不断的
    0.79
     ceo
    0.78
     unsplash
    0.77
    ense
    0.76
    Activations Density 0.067%

    No Known Activations