© 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. 175135
    Prev
    Next
    INDEX
    Explanations

    access thecollection withinmore simplepush and

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

    handling whitespace and separators

    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
    ྥ
    0.75
     אוי
    0.59
    ྵ
    0.55
    🌋
    0.54
     конди
    0.52
    缛
    0.51
    泷
    0.51
    诵
    0.50
    啮
    0.50
    ょう
    0.50
    POSITIVE LOGITS
     website
    0.51
    esteem
    0.51
     recognizes
    0.50
    ’
    0.50
     provides
    0.48
     bertujuan
    0.48
    providecommand
    0.47
     service
    0.46
     GmbH
    0.46
     strives
    0.46
    Activations Density 0.000%

    No Known Activations