© 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. 13922
    Prev
    Next
    INDEX
    Explanations

    question marks and colons

    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
     vider
    -2.23
    蕯
    -2.19
     Répondre
    -2.16
     reager
    -2.05
     Nieuws
    -2.03
     individuel
    -2.02
     dezelve
    -2.00
    ኧ
    -2.00
    Their
    -1.99
    儈
    -1.98
    POSITIVE LOGITS
     beeindruck
    2.00
     of
    1.98
     including
    1.94
     “
    1.91
     obecnie
    1.86
     but
    1.83
     is
    1.79
    ፻
    1.79
     aquellas
    1.78
    合作伙伴
    1.77
    Activations Density 0.003%

    No Known Activations