© 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. 14870
    Prev
    Next
    INDEX
    Explanations

    I manipulate words

    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
     didn
    1.08
     went
    1.03
     próprios
    1.00
     couldn
    0.98
     could
    0.93
     will
    0.91
    <unused2223>
    0.90
     would
    0.89
     took
    0.88
     grew
    0.87
    POSITIVE LOGITS
     Sedangkan
    0.77
     evitando
    0.71
    clientWidth
    0.70
    此
    0.68
     પ્રકાર
    0.68
    其次
    0.68
    เพื่อให้
    0.68
     leitura
    0.67
     terjadinya
    0.67
    Parsing
    0.67
    Activations Density 0.001%

    No Known Activations