© 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. 7539
    Prev
    Next
    INDEX
    Explanations

    vertebrae and southeastern regions

    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>
    -2.86
    a
    -2.44
    )
    -2.25
    ệc
    -2.20
    s
    -2.16
    exao
    -2.16
     hundred
    -2.16
     adorable
    -2.14
    -2.13
    t
    -2.05
    POSITIVE LOGITS
    說
    2.77
    </h3>
    2.69
    er
    2.67
    an
    2.66
    脔
    2.64
    錵
    2.59
     garantis
    2.58
    ༀ
    2.56
    揠
    2.55
    。。。
    2.52
    Activations Density 0.017%
    No Known Activations