© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    project structure

    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
     duż
    0.88
    ٬
    0.82
    totals
    0.78
    \|
    0.78
    Мы
    0.77
    鬨
    0.77
     সক্রিয়
    0.76
    ICLES
    0.76
    AK
    0.75
    देख
    0.74
    POSITIVE LOGITS
     $\%
    1.07
    ringle
    1.06
    此之外
    1.05
    Pda
    0.98
     Ngoài
    0.97
    Rồi
    0.96
     disso
    0.95
     তীর
    0.95
    感じ
    0.93
     вина
    0.92
    Activations Density 0.001%

    No Known Activations