© 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. 104519
    Prev
    Next
    INDEX
    Explanations

    obtaining permission or consent

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

    describing actions or states

    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
     Shakespeare
    0.46
     comedian
    0.45
     birdseye
    0.44
     reconsideration
    0.44
    옵
    0.42
    흠
    0.42
     것도
    0.41
     Milton
    0.41
     आपल्याला
    0.41
     Lindsey
    0.41
    POSITIVE LOGITS
     行っ
    0.63
    ')));
    0.48
    QH
    0.48
     दोषियों
    0.48
     πραγ
    0.46
    ）」
    0.46
    ឍ
    0.45
     अस्पतालों
    0.45
    CriteriaUtils
    0.45
     તેના
    0.45
    Activations Density 0.000%

    No Known Activations