© 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. 144906
    Prev
    Next
    INDEX
    Explanations

    headache, ball, datasets, belt

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

    code snippets and programming terms

    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
    𝚍
    0.48
    輛
    0.47
     Ogden
    0.46
    ើត
    0.44
     enfermos
    0.43
    មា
    0.43
    vict
    0.42
    ீர்க
    0.42
    ㄉ
    0.41
     мероприятий
    0.41
    POSITIVE LOGITS
     చరిత్ర
    0.46
     Königreich
    0.46
     König
    0.46
     Liga
    0.46
    ۔
    0.45
    meyi
    0.44
    โห
    0.44
    ToListAsync
    0.42
    ่า
    0.42
     Serbia
    0.42
    Activations Density 0.000%

    No Known Activations