© 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. 155600
    Prev
    Next
    INDEX
    Explanations

    undoubtedly total

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

    find all

    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
     Maybe
    0.56
     So
    0.54
     j
    0.53
     Liberty
    0.52
     NDA
    0.52
     Cub
    0.51
     X
    0.50
     SO
    0.50
     Ah
    0.49
     Hat
    0.49
    POSITIVE LOGITS
    그
    0.51
    ラブ
    0.50
    testimon
    0.50
    กับ
    0.50
    티브
    0.50
    تاریخ
    0.49
    함
    0.49
    برای
    0.49
    चानक
    0.49
    조건
    0.48
    Activations Density 0.000%

    No Known Activations