© 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. 97090
    Prev
    Next
    INDEX
    Explanations

    rulemaking, addressing, company, policies

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

    focused bond

    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
     pojed
    0.44
     horrend
    0.43
    ੱਸ
    0.43
    <0x0D>
    0.41
     petite
    0.41
     delicioso
    0.41
     fuerte
    0.41
     terrible
    0.40
    ":[{"
    0.40
    約
    0.40
    POSITIVE LOGITS
     rulemaking
    0.48
     addressing
    0.47
    定义的
    0.46
     şirket
    0.46
    婧
    0.46
     geschaffen
    0.45
     الشركات
    0.44
    شركة
    0.43
     সংশোধন
    0.43
    sect
    0.43
    Activations Density 0.000%

    No Known Activations