© 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. 65171
    Prev
    Next
    INDEX
    Explanations

    how can I or you

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

    how can

    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
     смогли
    0.48
     クリスマス
    0.46
    ណ្ឌ
    0.46
     tenue
    0.45
    珉
    0.45
    UpSync
    0.45
     ブル
    0.44
     सिसोदिया
    0.44
     وصحبه
    0.44
     prakty
    0.44
    POSITIVE LOGITS
    an
    0.55
    ich
    0.49
    we
    0.48
    lı
    0.48
     быть
    0.48
    et
    0.47
    en
    0.46
    you
    0.46
    a
    0.46
    ocean
    0.46
    Activations Density 0.020%

    No Known Activations