© 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. 173592
    Prev
    Next
    INDEX
    Explanations

    prescribed medication

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

    user prompts or queries

    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
     vutto
    0.53
    ;?>
    0.52
    𒃲
    0.51
    hasClass
    0.48
    скохозяй
    0.46
    jsonObject
    0.45
     issn
    0.45
    mataspid
    0.45
    subtitle
    0.44
    AWSJavaScriptSDK
    0.44
    POSITIVE LOGITS
     Air
    0.56
     Artist
    0.47
    /
    0.47
     contexte
    0.46
     Ahora
    0.46
     Rubber
    0.46
    ート
    0.43
     Hmm
    0.43
     recognize
    0.43
     hometown
    0.42
    Activations Density 0.000%

    No Known Activations