© 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. 34-GEMMASCOPE-RES-131K
    7. 117103
    Prev
    Next
    INDEX
    Explanations

    ipsilateral, abbreviations, ps

    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_34/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
     Tre
    -0.73
    ToScroll
    -0.72
    to
    -0.72
     mir
    -0.71
     tuttavia
    -0.71
     exemplar
    -0.71
    agie
    -0.70
     Fil
    -0.69
    然而
    -0.68
    im
    -0.67
    POSITIVE LOGITS
    פס
    0.84
    UMES
    0.78
    oriasis
    0.77
     pasang
    0.75
    ciles
    0.74
    ǝ
    0.74
    擰
    0.73
    YCH
    0.73
     Gute
    0.72
     avancée
    0.72
    Activations Density 0.037%

    No Known Activations