© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43443
    Prev
    Next
    INDEX
    Explanations

    code, data, or 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
     acelerar
    -1.52
     —
    -1.52
     efectuar
    -1.50
    ’
    -1.49
     уже
    -1.45
     одной
    -1.44
     incorporar
    -1.38
     یکی
    -1.31
     negociar
    -1.30
     aliviar
    -1.30
    POSITIVE LOGITS
     of
    2.39
     for
    2.02
     also
    1.52
    ☡
    1.51
     vna
    1.49
     that
    1.48
    ༵
    1.42
    翆
    1.41
     boty
    1.41
     altijd
    1.41
    Activations Density 0.049%

    No Known Activations