© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27465
    Prev
    Next
    INDEX
    Explanations

    technical documentation keywords and code elements

    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
     Políticas
    -1.02
    그리고
    -0.98
     Février
    -0.98
    ಝ
    -0.96
    yendo
    -0.94
     oxu
    -0.94
    ″]
    -0.93
    侪
    -0.91
    xim
    -0.91
    teig
    -0.91
    POSITIVE LOGITS
     to
    1.32
     and
    1.21
    もちゃ
    1.03
    ldap
    0.99
     which
    0.99
     especially
    0.96
    里有
    0.94
    UpdatedBy
    0.94
     as
    0.93
    /
    0.91
    Activations Density 0.001%

    No Known Activations