© 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. 48606
    Prev
    Next
    INDEX
    Explanations

    let go, let me, let's

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

    apology, let us, goals for, airport, rounds

    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
    ท
    0.52
    menopausal
    0.52
    ⸱
    0.51
    ฤษ
    0.51
    멸
    0.50
    สม
    0.50
    ิลป
    0.48
    odesmium
    0.48
    สะอาด
    0.47
    RatingDiff
    0.47
    POSITIVE LOGITS
     City
    0.58
     Investor
    0.54
     escrow
    0.54
     Airport
    0.53
     bạn
    0.52
     I
    0.51
     cellphone
    0.51
     Fiat
    0.50
     audi
    0.50
     airport
    0.48
    Activations Density 0.000%

    No Known Activations