© 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. 30638
    Prev
    Next
    INDEX
    Explanations

    name given

    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
    chnung
    -0.80
    gré
    -0.79
    Lä
    -0.73
    Allows
    -0.73
    iddle
    -0.73
    ריך
    -0.71
    Dni
    -0.70
    jame
    -0.69
    eien
    -0.69
    ल्या
    -0.69
    POSITIVE LOGITS
     given
    5.41
    given
    3.92
     diberikan
    3.61
     provided
    3.25
    Given
    3.13
     offered
    2.98
    给
    2.95
     Given
    2.88
     GIVEN
    2.84
     give
    2.83
    Activations Density 0.213%

    No Known Activations