© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 174967
    Prev
    Next
    INDEX
    Explanations

    testing code and procedures

    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
    <0x0D>
    0.51
    et
    0.49
    рифт
    0.47
     Personnel
    0.47
     Jeremy
    0.47
     FTSE
    0.46
     Solutions
    0.46
     delighted
    0.46
     soluzioni
    0.45
    ik
    0.45
    POSITIVE LOGITS
     المح
    0.43
     విధాన
    0.40
     المرحله
    0.39
    低的
    0.39
    痨
    0.38
    cube
    0.38
     خراب
    0.38
     हत्याकांड
    0.38
     الف
    0.38
     المتوسط
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.