© 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. 66863
    Prev
    Next
    INDEX
    Explanations

    end of blocks or data

    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
    during
    -2.38
    relatively
    -2.23
    extremely
    -2.19
    despite
    -2.13
    directly
    -2.11
    becoming
    -2.11
    ⚋
    -2.06
    </strong>
    -2.02
     développer
    -1.99
    several
    -1.98
    POSITIVE LOGITS
     With
    2.33
    }$.
    2.20
     Some
    2.11
     Hundreds
    2.00
    我们
    1.94
    澳門
    1.92
    為了
    1.91
     pemasaran
    1.86
     Several
    1.83
     Numerous
    1.83
    Activations Density 0.009%

    No Known Activations