© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 45285
    Prev
    Next
    INDEX
    Explanations

    granting a user

    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_31_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
     얼
    0.50
    燴
    0.45
    撸
    0.43
    iliate
    0.43
    Certified
    0.43
     นั่น
    0.42
    Market
    0.42
     ateliers
    0.42
     Genomics
    0.41
    MISSIONS
    0.41
    POSITIVE LOGITS
    abar
    0.46
     Zanz
    0.42
     harmless
    0.42
     diferente
    0.40
     inadvert
    0.40
     involuntary
    0.40
     averse
    0.39
    ង
    0.38
     unintentional
    0.38
     rebellious
    0.37
    Activations Density 0.002%

    No Known Activations