© 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. 18312
    Prev
    Next
    INDEX
    Explanations

    section episode unit chapter

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

    variations of others

    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
    اا
    0.55
    𝗮
    0.52
    .
    0.49
    માં
    0.48
    ുമ
    0.48
     заседа
    0.47
    รา
    0.47
    א
    0.47
    ric
    0.46
    orientation
    0.46
    POSITIVE LOGITS
     Г
    0.43
     fakta
    0.43
     Америки
    0.41
     absurdity
    0.41
     dowol
    0.41
     الصوت
    0.40
     morb
    0.40
     otras
    0.39
     ثلاث
    0.39
     firepower
    0.39
    Activations Density 0.007%

    No Known Activations