© 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. 220272
    Prev
    Next
    INDEX
    Explanations

    we appreciate

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

    conspiracy theories and fringe topics

    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
    ବ
    0.53
    비스
    0.51
    ститут
    0.51
    廚
    0.48
    사각형
    0.47
    불어
    0.47
    کز
    0.46
    ून
    0.44
     createImage
    0.44
    াজ
    0.44
    POSITIVE LOGITS
     indígen
    0.49
     libert
    0.45
     nach
    0.44
    tbl
    0.44
    nach
    0.44
    秏
    0.44
    haupt
    0.44
     พอ
    0.44
    hwa
    0.43
    olik
    0.43
    Activations Density 0.000%

    No Known Activations