© 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. 65117
    Prev
    Next
    INDEX
    Explanations

    accordance with

    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
    ’，
    -2.38
    ⎚
    -2.25
    </h1>
    -2.11
    
    -2.05
    asjoner
    -1.97
    なども
    -1.97
     Украина
    -1.97
    ENODE
    -1.93
    âmara
    -1.90
     они
    -1.88
    POSITIVE LOGITS
    ↵
    2.75
    “(
    2.55
    “
    2.36
    $
    2.27
    所说的
    2.13
    “[
    1.96
    7
    1.91
    th
    1.91
    U
    1.88
    Ꮴ
    1.88
    Activations Density 0.007%

    No Known Activations