© 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. 30347
    Prev
    Next
    INDEX
    Explanations

    Q or GOP content

    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
     goblet
    -0.89
    anyuan
    -0.76
     الحالي
    -0.75
     Jalisco
    -0.73
    fromJson
    -0.73
    codehaus
    -0.72
    Ʒ
    -0.72
    יך
    -0.72
    enné
    -0.72
    бочки
    -0.71
    POSITIVE LOGITS
     Tag
    1.58
    Tag
    1.43
     tag
    1.37
     tagging
    1.16
    tag
    1.13
     TAG
    1.11
     tags
    1.08
     Tags
    1.06
     text
    0.95
    TAG
    0.90
    Activations Density 0.010%

    No Known Activations