© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    phrasal continuations

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

    command instructions

    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
    ,
    0.29
     circuitry
    0.27
     cramped
    0.27
     LinearLayout
    0.27
     skincare
    0.26
     cabling
    0.26
     whatnot
    0.26
     constellation
    0.25
     Snacks
    0.25
     Spine
    0.25
    POSITIVE LOGITS
    நீங்கள்
    0.40
    7
    0.39
    6
    0.38
    आज
    0.38
    kontrol
    0.38
     هذا
    0.38
    8
    0.38
    siehe
    0.37
    Ნ
    0.37
    ТС
    0.37
    Activations Density 0.228%

    No Known Activations