© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63187
    Prev
    Next
    INDEX
    Explanations

    list items or key phrases

    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_65k_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
     Sketches
    0.46
     Mill
    0.43
     appena
    0.42
     Avalon
    0.42
     Clap
    0.41
     Tycho
    0.41
    𒂍
    0.40
     Mille
    0.40
     रविवार
    0.39
     Cray
    0.39
    POSITIVE LOGITS
    received
    0.43
    eal
    0.40
    agent
    0.39
    ene
    0.39
    ഹ്ലാദ
    0.38
    expert
    0.37
    we
    0.37
    Ҭ
    0.37
    de
    0.37
    re
    0.36
    Activations Density 0.001%

    No Known Activations