© 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. 8013
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    </b>
    -4.31
    derdag
    -2.75
    ва
    -2.75
    </h1>
    -2.63
     lament
    -2.53
     решения
    -2.47
    end
    -2.44
    –
    -2.39
    룬
    -2.38
    </i>
    -2.36
    POSITIVE LOGITS
    ，“
    2.92
    Ꭳ
    2.81
     aanzien
    2.81
     gebeurt
    2.61
    縯
    2.58
     zorgt
    2.55
     anio
    2.53
    鱘
    2.53
     ,‬
    2.53
    が生
    2.53
    Activations Density 0.006%

    No Known Activations