© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 524
    Prev
    Next
    INDEX
    Explanations

    half minute hello highest chat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Sarkar
    0.76
     Cous
    0.75
     Camer
    0.73
    崎
    0.71
     Soviets
    0.68
    acon
    0.67
    croll
    0.66
     Spicer
    0.66
     Slick
    0.66
     modal
    0.63
    POSITIVE LOGITS
    H
    2.17
     H
    2.01
    h
    1.83
     h
    1.61
    HH
    1.58
    Hs
    1.56
    HB
    1.43
    HM
    1.41
    HI
    1.41
    hx
    1.40
    Activations Density 2.961%

    No Known Activations