© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    central, bissell, step, aqua, floor, vinyl, first, bedroom, kids, elton

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

    enjoying red meat

    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
    BOOT
    0.45
    fficacy
    0.40
    ניות
    0.39
    گزاری
    0.39
    ক্তির
    0.39
    妍
    0.38
     apporter
    0.38
     Boynton
    0.38
     بست
    0.38
    ွဲ
    0.37
    POSITIVE LOGITS
     さん
    0.50
     公式
    0.44
    Н
    0.44
    s
    0.44
    omethane
    0.44
    amag
    0.42
    sman
    0.41
     আশ্বাস
    0.41
     Formula
    0.41
     lask
    0.40
    Activations Density 0.025%

    No Known Activations