© 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. 80319
    Prev
    Next
    INDEX
    Explanations

    properties, stocks, stories, best way

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

    skill learning

    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
     Unternehmer
    0.47
     znacz
    0.46
     больше
    0.45
     список
    0.43
     ダブル
    0.43
     seznam
    0.43
     меньше
    0.43
    煽
    0.42
     ἡ
    0.42
     сдела
    0.42
    POSITIVE LOGITS
    TE
    0.53
    STE
    0.52
    REN
    0.50
    LOLLIPOP
    0.50
    HO
    0.50
    MENT
    0.49
    TEN
    0.48
    CR
    0.48
    েইন
    0.47
    TER
    0.46
    Activations Density 0.000%

    No Known Activations