© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15002
    Prev
    Next
    INDEX
    Explanations

    control, value, action

    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
    es
    0.46
     ly
    0.46
     Gr
    0.45
    াধিকার
    0.45
    u
    0.45
     Initial
    0.44
    ావ
    0.43
    ole
    0.42
    o
    0.42
    uet
    0.42
    POSITIVE LOGITS
     contrô
    0.53
     dévo
    0.52
    attaque
    0.51
    ད
    0.50
     attaqu
    0.49
     acteurs
    0.49
     mengungkapkan
    0.48
    เน
    0.47
     appré
    0.47
     valeur
    0.47
    Activations Density 0.001%

    No Known Activations