© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126996
    Prev
    Next
    INDEX
    Explanations

    well dressed

    np_acts-logits-general · gemini-2.5-flash-lite

    prime numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    at
    0.59
    v
    0.52
    on
    0.50
     war
    0.49
     identification
    0.48
     co
    0.48
     am
    0.47
    acions
    0.47
     g
    0.47
    ịa
    0.47
    POSITIVE LOGITS
    ('|
    0.55
    nilvadipine
    0.51
     Nationality
    0.50
    ニス
    0.49
     Catering
    0.49
     inactivació
    0.49
    ShowWindow
    0.48
    ಸ್ತಕ
    0.48
     Entertain
    0.47
     Freshman
    0.47
    Activations Density 0.000%

    No Known Activations