© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8377
    Prev
    Next
    INDEX
    Explanations

    sunlight and solar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ور
    1.39
    𝐞
    1.28
    ឫ
    1.28
    dbo
    1.27
    𝕥
    1.26
    ievements
    1.21
    𝐮
    1.20
    isodes
    1.19
    oze
    1.19
     frameN
    1.18
    POSITIVE LOGITS
     الشمس
    1.82
     shining
    1.71
     sunlight
    1.67
    耀
    1.63
     airy
    1.61
    照射
    1.51
     matahari
    1.49
     Sunlight
    1.49
     irradiance
    1.49
     luminosity
    1.48
    Activations Density 0.297%

    No Known Activations