© 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. 22-GEMMASCOPE-RES-131K
    7. 66173
    Prev
    Next
    INDEX
    Explanations

    biographies of people

    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_22/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
     is
    -1.15
     but
    -1.08
    </i>
    -1.04
    兵衛
    -1.04
     to
    -1.01
     $
    -1.00
     것이다
    -0.99
    InstrumentedTest
    -0.96
     access
    -0.96
     abduction
    -0.93
    POSITIVE LOGITS
     someone
    1.38
     encantador
    1.30
    ผู้
    1.20
    Funcionario
    1.14
    UARIO
    1.13
    dapat
    1.13
     yourself
    1.13
    celotti
    1.13
     young
    1.12
     female
    1.12
    Activations Density 0.111%

    No Known Activations