© 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. 227973
    Prev
    Next
    INDEX
    Explanations

    want readers or want to

    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
    하고
    0.50
    actoring
    0.49
     회
    0.49
    ativo
    0.48
     돌아
    0.48
    Strafpunkte
    0.46
    조건
    0.46
    उने
    0.46
    ί
    0.45
    할
    0.45
    POSITIVE LOGITS
    ኩ
    0.50
     vanes
    0.46
     moms
    0.45
     initializes
    0.44
     mentors
    0.43
     ylab
    0.43
     zippers
    0.43
     zoon
    0.42
     anthracene
    0.42
    Fonts
    0.42
    Activations Density 0.000%

    No Known Activations