© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57653
    Prev
    Next
    INDEX
    Explanations

    an apparent

    np_acts-logits-general · gemini-2.5-flash-lite

    likely following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Distributors
    0.43
    oodoo
    0.42
    ranton
    0.41
    >(){
    0.41
     जाहिर
    0.40
    aughan
    0.40
     でき
    0.40
    ේව
    0.40
     একট
    0.40
    嚨
    0.40
    POSITIVE LOGITS
     SEX
    0.48
     sweeping
    0.48
     LARGE
    0.45
     määr
    0.44
     cinematic
    0.43
     longitudinal
    0.43
    ως
    0.43
     spann
    0.43
     SQUARE
    0.42
     diantaranya
    0.42
    Activations Density 0.000%

    No Known Activations