© 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. 62306
    Prev
    Next
    INDEX
    Explanations

    additional $

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

    Marketing is Key

    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
     It
    0.53
     executes
    0.52
     มัน
    0.48
    Г
    0.47
     it
    0.46
    ;
    0.45
    Д
    0.45
     executed
    0.44
     ln
    0.44
     Sixty
    0.44
    POSITIVE LOGITS
    もしくは
    0.50
    ബരിമല
    0.45
    تباه
    0.45
    っち
    0.43
    رحله
    0.42
    ولی
    0.42
    祸
    0.42
     علیہ
    0.42
    လိ
    0.41
    思った
    0.41
    Activations Density 0.000%

    No Known Activations