© 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. 77462
    Prev
    Next
    INDEX
    Explanations

    altering names for privacy

    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
    DeclareMath
    -0.84
    导演
    -0.83
    bø
    -0.81
     NED
    -0.80
     authoritative
    -0.78
     stoppage
    -0.77
     berücksichtigen
    -0.76
    Authorize
    -0.75
     estran
    -0.73
     Authorized
    -0.73
    POSITIVE LOGITS
     anonymity
    3.00
     identifying
    2.50
     identity
    2.41
     anonymous
    2.20
     identities
    2.19
     anonim
    2.16
    Anonym
    2.16
    Identi
    2.16
    identi
    2.14
     anonym
    2.14
    Activations Density 0.058%

    No Known Activations