© 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. 22-GEMMASCOPE-2-RES-16K
    7. 603
    Prev
    Next
    INDEX
    Explanations

    dynamic, auto, and open types

    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_22_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
    问题
    0.71
     생각
    0.64
     etc
    0.63
    较
    0.62
    役
    0.60
    etc
    0.58
    If
    0.58
    方
    0.57
    songs
    0.57
     If
    0.56
    POSITIVE LOGITS
    化的
    1.36
     पद्धतीने
    1.32
    ized
    1.31
    ised
    1.22
    版的
    1.21
     versions
    1.17
    isierten
    1.17
    izable
    1.15
    izado
    1.14
    式の
    1.09
    Activations Density 1.229%

    No Known Activations