Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 99468
    Prev
    Next
    INDEX
    Explanations

    money transfer requests

    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_40_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
     portals
    0.43
     attack
    0.40
     corners
    0.39
     carrier
    0.38
     displ
    0.38
     tackle
    0.38
     Ashton
    0.38
    读
    0.37
    ктор
    0.37
     corner
    0.36
    POSITIVE LOGITS
     सिंपली
    0.44
     szükség
    0.42
     ziek
    0.40
     sostanz
    0.40
     especializados
    0.40
    忄
    0.39
    agl
    0.39
     vissa
    0.39
    ẍ
    0.39
    Integrated
    0.38
    Activations Density 0.001%

    No Known Activations