© 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. 131433
    Prev
    Next
    INDEX
    Explanations

    creating your, the most

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

    title suggestions or alternative names

    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
    бед
    0.50
     negligent
    0.50
     neglect
    0.47
    裒
    0.47
     neglecting
    0.46
     сна
    0.46
     sheared
    0.45
     fracturing
    0.43
     acreage
    0.43
     neglects
    0.43
    POSITIVE LOGITS
    óp
    0.52
    ürk
    0.50
     가
    0.50
    새
    0.48
    ukaemia
    0.47
    Ó
    0.47
    áln
    0.47
    edores
    0.47
    കോ
    0.47
    É
    0.47
    Activations Density 0.001%

    No Known Activations