© 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. 183717
    Prev
    Next
    INDEX
    Explanations

    business services, professional guidance

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

    regions, people, alternatives

    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
    隍
    0.52
    帮忙
    0.47
    幽
    0.47
    ුවන්
    0.47
    랗
    0.46
    泵
    0.45
    ы
    0.45
    厡
    0.45
    ﺄ
    0.44
    уч
    0.44
    POSITIVE LOGITS
    why
    0.46
     consec
    0.46
    nya
    0.44
     sustained
    0.43
     commas
    0.42
     변화
    0.41
    ட்டா
    0.40
    unjungi
    0.40
     why
    0.40
     expectancy
    0.40
    Activations Density 0.000%

    No Known Activations