© 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. 63284
    Prev
    Next
    INDEX
    Explanations

    as a role or identity

    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
    jand
    -1.01
    timme
    -0.96
    منی
    -0.93
    鱿
    -0.93
    razine
    -0.92
    niti
    -0.90
    ***/
    -0.89
    fol
    -0.88
    😲
    -0.88
    🕵
    -0.87
    POSITIVE LOGITS
     a
    2.39
     individuals
    1.65
     humans
    1.59
     citizens
    1.48
     professionals
    1.35
     leaders
    1.29
     representatives
    1.16
    nissan
    1.16
     members
    1.14
     consumers
    1.14
    Activations Density 0.027%

    No Known Activations