© 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. 142446
    Prev
    Next
    INDEX
    Explanations

    business, extra fee, lock

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

    riddled with, issues, graphs, POS, exploits, slightly unusual, blood pressure

    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
    जीटी
    0.61
     Ricci
    0.54
    সা
    0.54
    ش
    0.51
     Núñez
    0.50
     ಗೌ
    0.49
     سع
    0.47
    स्की
    0.47
     imprescind
    0.46
    mathml
    0.46
    POSITIVE LOGITS
     аз
    0.50
    ཅ
    0.44
    เข้าใจ
    0.44
     extinguishing
    0.44
     azimuthal
    0.43
     בית
    0.42
    фан
    0.42
    竝
    0.41
     excellent
    0.40
    ethyst
    0.40
    Activations Density 0.000%

    No Known Activations