© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128051
    Prev
    Next
    INDEX
    Explanations

    HTML entities and escapes

    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
    0
    -2.42
    They
    -2.36
    <bos>
    -2.28
    It
    -2.22
    相変わらず
    -2.17
    那個
    -2.16
     adhesivo
    -2.08
    橚
    -2.06
    before
    -2.06
     “
    -1.99
    POSITIVE LOGITS
     you
    2.88
     and
    2.70
     in
    2.23
    錚
    2.02
     at
    2.00
     see
    1.98
     sebagian
    1.91
    ⃙
    1.88
     sosok
    1.88
     between
    1.86
    Activations Density 0.007%

    No Known Activations