© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138306
    Prev
    Next
    INDEX
    Explanations

    buffet table

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

    communication systems and speech

    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
     Heels
    0.53
    炇
    0.52
    是
    0.48
     मतदाताओं
    0.48
    笫
    0.48
     Enrollment
    0.47
    广告
    0.47
    营收
    0.47
    芡
    0.46
    㹮
    0.46
    POSITIVE LOGITS
    า
    0.63
    otype
    0.55
    ten
    0.53
     ulterior
    0.49
    hares
    0.49
     allevi
    0.49
     scherm
    0.48
     dedic
    0.47
    ходить
    0.47
     campan
    0.46
    Activations Density 0.000%

    No Known Activations