© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 83496
    Prev
    Next
    INDEX
    Explanations

    basic categorization and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issors
    0.42
    뉜
    0.42
    intersects
    0.42
    CHECKS
    0.41
    efficients
    0.40
    habit
    0.40
    ethers
    0.39
    signals
    0.38
    UserProg
    0.38
    increment
    0.37
    POSITIVE LOGITS
     Symmetric
    0.52
     symmetric
    0.47
     TYPES
    0.46
    最
    0.45
     基本
    0.45
    㐱
    0.44
     Hidden
    0.44
     basic
    0.44
     Homer
    0.44
     symmetrical
    0.43
    Activations Density 0.007%

    No Known Activations