© 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. 105853
    Prev
    Next
    INDEX
    Explanations

    sponsored to, prepare for, mutual initiatives

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

    initial setup or phase

    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
    গের
    0.48
    ۢ
    0.48
    ریح
    0.47
     했
    0.46
    哨
    0.46
     COLLATE
    0.45
    ные
    0.45
    वासी
    0.44
     KEYUP
    0.44
    했
    0.44
    POSITIVE LOGITS
    Abroad
    0.51
    Make
    0.49
    Asie
    0.48
     나라
    0.47
    West
    0.46
    Into
    0.46
    ന്വേഷ
    0.46
    Feeling
    0.46
    Remember
    0.45
    Wedding
    0.45
    Activations Density 0.000%

    No Known Activations