© 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. 112804
    Prev
    Next
    INDEX
    Explanations

    ranking or top position

    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
    nių
    -1.70
    Soorten
    -1.45
     pouze
    -1.45
    :
    -1.43
    ~~~~~~~
    -1.42
     leopardo
    -1.40
    jaman
    -1.38
    "__
    -1.38
    umerable
    -1.37
     swarming
    -1.37
    POSITIVE LOGITS
     tył
    1.99
     also
    1.70
    </h2>
    1.64
     herida
    1.45
     montaż
    1.44
    d
    1.44
    Недостатки
    1.40
     prized
    1.39
     должны
    1.37
    の準備
    1.36
    Activations Density 0.032%

    No Known Activations