© 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. 8227
    Prev
    Next
    INDEX
    Explanations

    sealed class

    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
     all
    -2.11
     on
    -2.05
     Perhaps
    -1.97
     more
    -1.95
     at
    -1.93
     each
    -1.88
     Certainly
    -1.88
     Undoubtedly
    -1.85
     out
    -1.84
     even
    -1.77
    POSITIVE LOGITS
     ۶
    2.05
    ſſen
    1.93
    ౬
    1.83
    ervices
    1.81
    providedIn
    1.80
     LIABLE
    1.80
    ogues
    1.77
    ፁ
    1.74
    姽
    1.74
    -<
    1.73
    Activations Density 0.082%

    No Known Activations