© 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. 157230
    Prev
    Next
    INDEX
    Explanations

    witty remark

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

    broken down with nuance

    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
    땄
    0.49
    ್ಧ
    0.48
    זו
    0.46
    ע
    0.46
    actifs
    0.45
    urètre
    0.45
    י
    0.45
    领取
    0.44
    ーーーー
    0.44
     তত্ব
    0.44
    POSITIVE LOGITS
     voltak
    0.53
     ಕೆಲವು
    0.50
     chờ
    0.47
     überras
    0.47
     فلسطين
    0.47
     hydrogen
    0.47
     kleiner
    0.46
     später
    0.46
     مصر
    0.46
     hatten
    0.46
    Activations Density 0.000%

    No Known Activations