© 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. 34-GEMMASCOPE-RES-131K
    7. 76857
    Prev
    Next
    INDEX
    Explanations

    not use

    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
     моди
    -0.71
    verifyException
    -0.69
    Acknowled
    -0.68
     Acknowled
    -0.68
     катего
    -0.67
     modi
    -0.66
    コーデ
    -0.63
     sanit
    -0.63
    面对
    -0.63
    tula
    -0.60
    POSITIVE LOGITS
     Zayed
    0.90
     Smack
    0.75
     sidste
    0.73
    ২
    0.73
    serialized
    0.68
     circulaire
    0.68
     samme
    0.67
     contener
    0.67
    asztok
    0.66
    łym
    0.66
    Activations Density 0.056%

    No Known Activations