© 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. 170308
    Prev
    Next
    INDEX
    Explanations

    locations, medical conditions, or life stages

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

    Filter check

    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
    帐
    0.47
    人用
    0.47
    记
    0.46
    上下文
    0.45
    后端
    0.45
    몹
    0.45
    贮
    0.44
    ．
    0.43
    篡
    0.43
    οδο
    0.42
    POSITIVE LOGITS
     drug
    0.56
     well
    0.55
     followers
    0.54
     faculty
    0.54
     kit
    0.53
     numerous
    0.53
     committee
    0.53
     diploma
    0.53
     revived
    0.53
     no
    0.52
    Activations Density 0.000%

    No Known Activations