© 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. 8338
    Prev
    Next
    INDEX
    Explanations

    peritoneovenous and auditory/visual

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

    val, gart, fra, med, vol, ഹ

    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
     Ecusson
    0.38
    喺
    0.35
     ！
    0.34
    ूट
    0.34
    फिर
    0.34
    」，
    0.33
    株式会社
    0.33
    ؔ
    0.33
     videojuegos
    0.33
    葛
    0.32
    POSITIVE LOGITS
    /-
    0.37
     regimes
    0.36
     이상의
    0.35
     цик
    0.33
     malaise
    0.33
    га
    0.33
     periods
    0.32
     وتح
    0.31
     baza
    0.31
    ষ্টা
    0.31
    Activations Density 0.025%

    No Known Activations