© 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. 68893
    Prev
    Next
    INDEX
    Explanations

    prodigy or prodigal

    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
    逦
    -2.55
     ...)
    -2.31
    鍇
    -2.30
    Ꮸ
    -2.28
    ).....
    -2.23
     jóvenes
    -2.19
    UAWEI
    -2.16
    肏
    -2.14
    .」
    -2.11
    ...)
    -2.09
    POSITIVE LOGITS
    ’
    3.61
    ”
    3.05
    {
    2.72
    Unfortunately
    2.36
    Again
    2.34
    —
    2.33
    良い
    2.31
    Clearly
    2.28
    Furthermore
    2.28
     of
    2.28
    Activations Density 0.003%

    No Known Activations