© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149116
    Prev
    Next
    INDEX
    Explanations

    different side effects of radiation

    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_29_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
    Wr
    0.77
    dives
    0.74
    克兰
    0.73
    mmas
    0.72
    Vendor
    0.72
    Istanbul
    0.70
    忤
    0.69
    Trong
    0.68
     consumes
    0.68
    ํ
    0.67
    POSITIVE LOGITS
     kinship
    0.84
     Folk
    0.82
     folk
    0.81
     Souls
    0.76
    颞
    0.74
     artistic
    0.74
     spatial
    0.74
     horoscope
    0.72
     souls
    0.71
    ไข
    0.70
    Activations Density 0.001%

    No Known Activations