© 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. 212650
    Prev
    Next
    INDEX
    Explanations

    sales funnels

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

    leaver or from via flow Anything

    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
    كيد
    0.50
     স্বাধীনতা
    0.45
     سبيل
    0.43
    compromising
    0.42
    AnchorStyles
    0.42
    有害
    0.42
    二年
    0.42
    ሑ
    0.41
    ണാ
    0.41
    澀
    0.41
    POSITIVE LOGITS
     maf
    0.49
     breakout
    0.49
    
    0.48
     pickup
    0.47
    ovým
    0.47
     dissolved
    0.46
     cave
    0.46
     payout
    0.46
     comeback
    0.45
     vint
    0.45
    Activations Density 0.001%

    No Known Activations