© 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. 41039
    Prev
    Next
    INDEX
    Explanations

    to Pakistan

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

    defending, aromas, contact

    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
     tempered
    0.47
    ens
    0.44
    🕹
    0.43
    🥕
    0.43
     vidhan
    0.43
    ujian
    0.42
    smöglichkeiten
    0.42
    en
    0.42
     etapas
    0.42
     zostały
    0.42
    POSITIVE LOGITS
    れない
    0.42
     Bikini
    0.42
     Republican
    0.42
    刺
    0.41
    薇
    0.41
     अवै
    0.40
    每月
    0.40
     Albion
    0.40
     неприят
    0.39
     Coal
    0.39
    Activations Density 0.000%

    No Known Activations