© 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. 22-GEMMASCOPE-RES-131K
    7. 15004
    Prev
    Next
    INDEX
    Explanations

    and the

    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_22/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
     Of
    -1.55
    觑
    -1.37
    práv
    -1.34
     samti
    -1.31
     foregoing
    -1.30
    initely
    -1.30
    larını
    -1.30
    dragen
    -1.30
     История
    -1.27
     Профиль
    -1.27
    POSITIVE LOGITS
     then
    2.19
     the
    2.05
     there
    1.68
    *
    1.63
    ]
    1.56
     it
    1.52
    ↵
    1.38
    </i>
    1.37
    {
    1.32
    </strong>
    1.30
    Activations Density 0.010%

    No Known Activations