© 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-262K
    7. 5161
    Prev
    Next
    INDEX
    Explanations

    haptic rigger MRI

    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_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
    m
    0.94
    م
    0.89
    l
    0.88
    r
    0.79
    t
    0.77
    y
    0.76
    d
    0.70
    in
    0.70
    p
    0.70
    ل
    0.69
    POSITIVE LOGITS
    ither
    0.65
    irc
    0.61
    isting
    0.58
    MRI
    0.57
    ō
    0.56
    Какой
    0.55
    autres
    0.55
    íc
    0.55
    asion
    0.55
    ugu
    0.54
    Activations Density 0.464%

    No Known Activations