© 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. 42073
    Prev
    Next
    INDEX
    Explanations

    left, right, or direction

    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
    {
    -2.17
    .
    -1.95
    </b>
    -1.92
     внутренних
    -1.84
     weitgehend
    -1.67
    未だ
    -1.63
     Still
    -1.60
    傾向
    -1.58
     beinahe
    -1.57
     erstmals
    -1.56
    POSITIVE LOGITS
     of
    2.34
    Ꮨ
    1.87
    ”،
    1.78
     rojas
    1.77
    ⢇
    1.73
    izoen
    1.70
    ⸥
    1.70
     nostro
    1.70
    ſſel
    1.67
    犼
    1.66
    Activations Density 0.015%

    No Known Activations