© 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. 10-GEMMASCOPE-RES-131K
    7. 20317
    Prev
    Next
    INDEX
    Explanations

    Checkbox, DropDown, names, adopters

    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_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
    $
    -2.78
    鮡
    -2.70
    ם
    -2.64
    嗵
    -2.61
    \
    -2.58
    ⛩
    -2.56
     ingrained
    -2.53
    tigten
    -2.50
    荖
    -2.41
    اتها
    -2.39
    POSITIVE LOGITS
    y
    3.44
     \
    3.11
    o
    3.06
    }:
    2.78
    en
    2.77
     s
    2.72
    i
    2.69
    –
    2.59
    .:
    2.59
     інших
    2.56
    Activations Density 0.010%

    No Known Activations