© 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. 38310
    Prev
    Next
    INDEX
    Explanations

    Is followed by Checked

    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
     another
    -1.02
    eronau
    -0.94
    another
    -0.93
     другой
    -0.93
    entification
    -0.91
     다른
    -0.84
     ebenfalls
    -0.84
     人生
    -0.83
    maining
    -0.83
    karta
    -0.83
    POSITIVE LOGITS
    !
    0.96
    tamol
    0.94
    icace
    0.93
     what
    0.93
    これだけ
    0.88
    節約
    0.85
     Isol
    0.84
    食べ物
    0.84
    Invariant
    0.84
    juje
    0.81
    Activations Density 0.001%

    No Known Activations