© 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. 238163
    Prev
    Next
    INDEX
    Explanations

    potentially discounted

    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
    👳
    0.54
     хлоп
    0.48
     অস্বীকার
    0.47
     illuminating
    0.47
    ilmente
    0.46
     weakens
    0.46
    Silence
    0.46
     ignores
    0.46
    ্স্ট
    0.45
     roared
    0.45
    POSITIVE LOGITS
    宜
    0.49
     ವ್ಯಾ
    0.47
    予
    0.44
    cd
    0.44
     gyven
    0.44
    実際に
    0.43
    AL
    0.43
    二手
    0.43
     विक्री
    0.42
    חי
    0.42
    Activations Density 0.001%

    No Known Activations