© 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. 54163
    Prev
    Next
    INDEX
    Explanations

    code enforcer

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

    evaluating judging fragments

    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
    odynam
    0.49
    媾
    0.48
    啊
    0.48
     Nib
    0.45
    ISupport
    0.44
    unde
    0.44
    最后一
    0.44
    lique
    0.43
    ZF
    0.43
     Riyadh
    0.43
    POSITIVE LOGITS
     reciting
    0.55
    дава
    0.53
    ေ
    0.51
     massaging
    0.50
     imitating
    0.50
     mimicking
    0.49
     різ
    0.49
    за
    0.48
     tortue
    0.48
     insuring
    0.48
    Activations Density 0.000%

    No Known Activations