© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    data, bytes, array conversion

    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
     infección
    1.04
     Corrosion
    1.00
    钚
    0.98
    jų
    0.97
    ConstPtr
    0.95
     Compression
    0.94
    ్ఞ
    0.93
    я
    0.92
     ')')
    0.92
     empate
    0.91
    POSITIVE LOGITS
    asikan
    1.05
    áv
    1.03
    ians
    1.03
    󠁴
    1.02
     نش
    1.01
    क्षेप
    0.99
    鮋
    0.99
     تد
    0.99
    isions
    0.98
     بشكل
    0.98
    Activations Density 0.020%

    No Known Activations