© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203385
    Prev
    Next
    INDEX
    Explanations

    attacking flair

    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
    ับ
    0.45
    เครื่อง
    0.44
    ап
    0.42
    ש
    0.42
     очи
    0.41
     машин
    0.41
    ซึ่ง
    0.40
     pretended
    0.40
     nCmd
    0.40
    errated
    0.39
    POSITIVE LOGITS
     ð
    0.55
     Shoe
    0.53
    ωσε
    0.53
     jog
    0.48
     tibia
    0.47
     cognac
    0.47
     forever
    0.46
     dioxide
    0.45
     joj
    0.45
    蹺
    0.45
    Activations Density 0.001%

    No Known Activations