© 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. 17-GEMMASCOPE-2-RES-16K
    7. 9072
    Prev
    Next
    INDEX
    Explanations

    css border radius

    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_17_width_16k_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
    ALERT
    0.92
    ALTER
    0.89
    ाब
    0.85
     جنس
    0.81
    难度
    0.81
    钽
    0.81
    엡
    0.81
    )}{
    0.81
    বাহী
    0.80
     nhiên
    0.79
    POSITIVE LOGITS
     BorderRadius
    1.22
     beim
    1.19
     zul
    1.19
     ikut
    1.17
     solub
    1.16
     cnpj
    1.16
     intelligents
    1.14
    sums
    1.13
     mocker
    1.12
     wsz
    1.12
    Activations Density 0.061%

    No Known Activations