© 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. 134901
    Prev
    Next
    INDEX
    Explanations

    area that. is rear your or department found of

    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
    chem
    0.53
    set
    0.50
    يت
    0.49
    vors
    0.46
    산
    0.43
     Set
    0.42
     ebbe
    0.42
    Set
    0.42
    وي
    0.41
    視
    0.41
    POSITIVE LOGITS
     忄
    0.59
    潍
    0.53
     میخ
    0.52
     кожу
    0.52
     βο
    0.49
    Municipal
    0.48
     hibernation
    0.48
     страхо
    0.48
    MktCap
    0.47
     spond
    0.47
    Activations Density 0.000%

    No Known Activations