© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4566
    Prev
    Next
    INDEX
    Explanations

    SQL data types and constraints

    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
    Pyrid
    0.41
     prophylaxis
    0.36
    Chill
    0.36
    .~\
    0.36
     moistened
    0.35
     bezpiecze
    0.35
     végétation
    0.35
    Przeczytaj
    0.34
     dwóch
    0.34
     hamstring
    0.33
    POSITIVE LOGITS
    ↵
    0.40
    nullable
    0.38
     DEFAULT
    0.36
     ,
    0.36
     nullable
    0.36
    NotNull
    0.36
    ，
    0.35
    truncate
    0.35
     String
    0.35
    required
    0.34
    Activations Density 0.036%

    No Known Activations