© 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. 70011
    Prev
    Next
    INDEX
    Explanations

    Zermatt, technologies, Dodoma

    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
    zhihu
    1.89
    桂
    1.85
    ковые
    1.82
     golpes
    1.75
    falls
    1.72
    LLA
    1.70
    accident
    1.69
    кового
    1.69
    จ
    1.69
    fight
    1.68
    POSITIVE LOGITS
    urator
    1.22
    akukannya
    1.07
    見える
    1.07
    ەوە
    1.07
     nonEmpty
    1.06
    ómo
    1.05
    porte
    1.04
    児童
    1.04
     аба
    1.04
     getopt
    1.01
    Activations Density 0.000%

    No Known Activations