© 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. 40039
    Prev
    Next
    INDEX
    Explanations

    hypothetical past conditions

    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
     Organisateur
    -2.06
    ཫ
    -1.91
    Terima
    -1.82
    コロナ禍
    -1.79
    ญี่ป
    -1.79
    Langkah
    -1.79
     dergleichen
    -1.75
     stupendous
    -1.74
    是如何
    -1.73
    喽
    -1.73
    POSITIVE LOGITS
    .
    2.92
    er
    2.08
     We
    2.00
     (
    1.95
     a
    1.89
    «
    1.88
    𓋼
    1.84
    ”
    1.74
     «
    1.69
     These
    1.69
    Activations Density 0.011%

    No Known Activations