© 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. 72390
    Prev
    Next
    INDEX
    Explanations

    not so much

    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
    textAlignment
    -1.05
     khong
    -1.02
     geleverd
    -0.96
    versible
    -0.93
    ResetPassword
    -0.92
     olmaz
    -0.91
     those
    -0.90
     bertanggung
    -0.90
    いたら
    -0.85
     inderdaad
    -0.85
    POSITIVE LOGITS
     actually
    0.98
     तो
    0.94
    直接
    0.94
     direkte
    0.91
    具体
    0.90
    真的
    0.90
     outright
    0.90
     actual
    0.89
     merely
    0.89
     direttamente
    0.89
    Activations Density 0.038%

    No Known Activations