© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126030
    Prev
    Next
    INDEX
    Explanations

    launch, test, conditions

    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
    t
    0.60
    achs
    0.47
    denes
    0.47
     Sympt
    0.46
    tól
    0.46
    ongs
    0.43
    tors
    0.43
    niają
    0.42
    ű
    0.42
    tas
    0.41
    POSITIVE LOGITS
     ishlab
    0.48
     Mining
    0.48
     kinetics
    0.47
    点セット
    0.47
     Rename
    0.47
     kinetic
    0.47
     mining
    0.46
    ણમાં
    0.44
     XIX
    0.44
    मपुर
    0.44
    Activations Density 0.003%

    No Known Activations