© 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. 26155
    Prev
    Next
    INDEX
    Explanations

    javascript code identifiers

    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
    ^{-}
    -1.00
    𝒎
    -0.90
     nép
    -0.86
     Americans
    -0.86
    stava
    -0.85
    Solution
    -0.85
     nyelv
    -0.84
     als
    -0.84
    Xc
    -0.84
     čtyř
    -0.84
    POSITIVE LOGITS
     Señora
    1.04
     these
    1.00
    hasData
    0.97
     barcel
    0.94
     antena
    0.94
     cajones
    0.92
     dacia
    0.90
    ଉ
    0.88
    Ꮀ
    0.88
    變化
    0.86
    Activations Density 0.007%

    No Known Activations