© 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. 57749
    Prev
    Next
    INDEX
    Explanations

    over fifty

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

    after the listed token

    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
     wagons
    0.46
     passengers
    0.44
     surprises
    0.44
     carriages
    0.42
     homosexuality
    0.41
    闢
    0.41
    諗
    0.40
    詎
    0.40
     inflows
    0.40
     surfers
    0.40
    POSITIVE LOGITS
    都被
    0.45
    扉
    0.44
    Founder
    0.44
    gtrsim
    0.44
     pues
    0.44
     choć
    0.43
     yuè
    0.43
    Engineering
    0.42
    \"",
    0.42
     óptica
    0.41
    Activations Density 0.000%

    No Known Activations