© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69770
    Prev
    Next
    INDEX
    Explanations

    diriges / dirige

    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_15_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
     Reichs
    1.73
    листи
    1.61
     indors
    1.57
     PoE
    1.51
    '],$
    1.49
    pap
    1.48
     stools
    1.46
     hins
    1.43
     meaty
    1.40
    userService
    1.39
    POSITIVE LOGITS
     înc
    1.62
    きましょう
    1.54
    єр
    1.43
    風格
    1.39
     există
    1.37
    ый
    1.35
     existe
    1.34
    矚
    1.33
     temperatur
    1.32
    گی
    1.32
    Activations Density 0.000%

    No Known Activations