© 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. 83627
    Prev
    Next
    INDEX
    Explanations

    planned destination, stored vCenter, especially nice, to cross

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

    describing specific types

    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
    뭍
    0.54
     gamanam
    0.50
    缆
    0.48
    峮
    0.47
    腮
    0.46
    impose
    0.46
     القناه
    0.45
     hinch
    0.45
    嬛
    0.45
    ihull
    0.44
    POSITIVE LOGITS
    ’
    0.53
     Российской
    0.45
     Africans
    0.44
     своїх
    0.42
     جدید
    0.41
     African
    0.41
    ‌های
    0.41
     طراحی
    0.41
     Milestone
    0.41
    ❿
    0.40
    Activations Density 0.000%

    No Known Activations