© 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. 29783
    Prev
    Next
    INDEX
    Explanations

    city ofworking hardweekly flashwas shot

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

    python lists, react web development

    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
    濘
    0.53
     déchir
    0.46
    လိ
    0.45
    ozen
    0.45
    렁
    0.45
    را
    0.44
     پسند
    0.44
    veld
    0.44
    Mapper
    0.44
    bmp
    0.44
    POSITIVE LOGITS
    铝
    0.50
    抓住
    0.48
    രിക്കുന്നത്
    0.47
     alumnus
    0.45
    关心
    0.44
    您
    0.43
    冲
    0.43
     `:`,
    0.43
     Freak
    0.42
    始终
    0.42
    Activations Density 0.000%

    No Known Activations