© 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. 17-GEMMASCOPE-2-RES-16K
    4. 15173
    Prev
    Next
    INDEX
    Explanations

    deposit or widthdraw

    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
    eing
    0.81
    ್
    0.79
    hematic
    0.77
    aing
    0.73
    e
    0.73
     всей
    0.73
    lected
    0.72
    ressing
    0.71
    aved
    0.70
    ept
    0.69
    POSITIVE LOGITS
    ار
    0.81
    ian
    0.68
    ли
    0.67
    酤
    0.67
    ແ
    0.67
    <unused217>
    0.66
    <0xF2>
    0.66
    ive
    0.65
    }")
    0.64
     الگ
    0.63
    Activations Density 0.030%

    No Known Activations