© 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. 105966
    Prev
    Next
    INDEX
    Explanations

    semester, project, forecasts, May

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

    work and rest

    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
     dificult
    0.47
    ﻅ
    0.46
     Cochran
    0.46
     diminu
    0.45
    時には
    0.44
    レ
    0.44
     criminally
    0.44
     воен
    0.43
    ነ
    0.43
    fiz
    0.43
    POSITIVE LOGITS
     Relationship
    0.46
     สำหรับ
    0.46
    HashTable
    0.46
     for
    0.46
     Relationships
    0.45
     Drinfeld
    0.45
     Sessions
    0.44
     olefins
    0.44
     Eating
    0.43
     ilişk
    0.43
    Activations Density 0.000%

    No Known Activations