© 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-16K
    7. 5004
    Prev
    Next
    INDEX
    Explanations

    OCR correction

    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_16k_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
     Slot
    0.41
     game
    0.41
     Slots
    0.37
     Poker
    0.37
     А
    0.37
     NA
    0.37
     slots
    0.37
     Ash
    0.37
     Game
    0.36
     Assassin
    0.35
    POSITIVE LOGITS
    还是
    0.42
    ..”
    0.41
    就需要
    0.40
     albeit
    0.39
    .”[
    0.39
    ຈະ
    0.39
    .”.
    0.38
     glycerol
    0.38
    .”)
    0.38
    …”
    0.37
    Activations Density 0.045%

    No Known Activations