© 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-65K
    7. 3893
    Prev
    Next
    INDEX
    Explanations

    tells `command` to do

    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_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
    写法
    0.45
    この
    0.45
     Recomend
    0.44
    鋯
    0.44
    ের
    0.43
     intestino
    0.43
     مکان
    0.43
    को
    0.43
    (""))
    0.42
    лює
    0.42
    POSITIVE LOGITS
     us
    0.83
     them
    0.72
     him
    0.72
     people
    0.68
     you
    0.65
     देम
    0.60
     вас
    0.57
    你
    0.55
     нас
    0.53
     você
    0.51
    Activations Density 0.164%

    No Known Activations