© 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. 152239
    Prev
    Next
    INDEX
    Explanations

    you shared information

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

    quoting movie or song lyrics

    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
     dürfen
    0.49
    传统
    0.44
    dan
    0.43
     overthrow
    0.42
    toj
    0.41
    ｄ
    0.41
    伝統
    0.40
     lightening
    0.40
    ｚ
    0.40
    Penis
    0.39
    POSITIVE LOGITS
     Lyons
    0.48
     Ambrose
    0.48
     Weiss
    0.48
     Mohan
    0.47
     Pietro
    0.47
     Altman
    0.46
     Giuliani
    0.46
     Emanuel
    0.46
     Ate
    0.46
     Грузии
    0.45
    Activations Density 0.000%

    No Known Activations