© 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. 105502
    Prev
    Next
    INDEX
    Explanations

    business, professional, or legal contexts

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

    cultural associations, letters, readiness, essential

    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
     هون
    0.53
    baikan
    0.48
     의한
    0.48
    할
    0.47
    čiti
    0.47
    Ꮃ
    0.46
     صور
    0.45
     ይመ
    0.45
     oblige
    0.44
     첫
    0.44
    POSITIVE LOGITS
     Measurement
    0.49
     Detector
    0.49
     interlocking
    0.48
    Measurement
    0.48
     detector
    0.47
     featured
    0.47
     Instrumented
    0.46
     alphanumeric
    0.46
    де
    0.46
     proclaimed
    0.46
    Activations Density 0.000%

    No Known Activations