© 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. 65403
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
     any
    -1.37
     or
    -1.14
     one
    -1.13
    ơi
    -1.09
    ICIÓN
    -1.07
     During
    -1.06
     will
    -0.98
     what
    -0.95
     when
    -0.94
     who
    -0.93
    POSITIVE LOGITS
     clearColor
    1.21
    などを
    1.11
    ༛
    1.03
    <bos>
    1.01
     Sahne
    0.98
     njego
    0.98
    を
    0.97
     astute
    0.96
    chromatic
    0.94
    Vendo
    0.94
    Activations Density 0.017%

    No Known Activations