© 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. 10-GEMMASCOPE-RES-131K
    4. 123868
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
     and
    -2.52
    schuhe
    -2.22
    占比
    -1.77
     зиму
    -1.76
    比较好
    -1.66
     getY
    -1.66
    atasi
    -1.66
    Procedimento
    -1.63
    えません
    -1.63
    能够
    -1.61
    POSITIVE LOGITS
    !!!!!!
    2.28
    !!!!!!!
    2.22
     also
    2.16
     each
    1.89
    。
    1.84
     then
    1.82
    或者是
    1.77
    !!!!!!!!
    1.76
     We
    1.74
     homicidio
    1.74
    Activations Density 0.086%

    No Known Activations