© 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. 115757
    Prev
    Next
    INDEX
    Explanations

    call to, we have, is cut, pinch together, retail store, riding ability

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

    departments, tiers, and ranges

    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
    <0x80>
    0.50
     Fellow
    0.46
     Eulerian
    0.42
     Jo
    0.41
     JM
    0.41
     ngay
    0.41
     Mitarbeiter
    0.41
     iaa
    0.40
    ugia
    0.40
     rối
    0.40
    POSITIVE LOGITS
    गार
    0.55
    MON
    0.54
    𝗪
    0.52
    VO
    0.49
    設計
    0.49
    DESIGN
    0.49
    लो
    0.48
    खान
    0.48
    STANDARD
    0.47
    ﻔ
    0.47
    Activations Density 0.000%

    No Known Activations