© 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. 57655
    Prev
    Next
    INDEX
    Explanations

    United States, operating systems, seasons, downloads, images

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

    sky, other, rates, url, developer

    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
    #
    0.40
    hey
    0.39
    emm
    0.39
    iga
    0.38
    Mobile
    0.38
    uye
    0.38
    fi
    0.38
    buy
    0.38
    usic
    0.38
    EM
    0.38
    POSITIVE LOGITS
     inflater
    0.41
     dismin
    0.41
    రిత్ర
    0.40
     イベント
    0.40
    ጨም
    0.40
    炆
    0.40
    淋
    0.40
    嵯
    0.40
    ิท
    0.39
    িট
    0.39
    Activations Density 0.056%

    No Known Activations