© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75035
    Prev
    Next
    INDEX
    Explanations

    position below threshold or limit

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     he
    -2.47
     be
    -2.25
    ・・・」
    -2.11
     is
    -2.08
    ㌧
    -2.00
    x
    -1.95
    」、
    -1.90
    at
    -1.89
    ist
    -1.89
     هناك
    -1.88
    POSITIVE LOGITS
     dengan
    2.95
     the
    2.94
    ﮯ
    2.88
     oferece
    2.69
     nacido
    2.59
    鮓
    2.58
    鹇
    2.48
    𖤣
    2.48
     famílias
    2.45
    狴
    2.45
    Activations Density 0.022%

    No Known Activations