© 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. 10391
    Prev
    Next
    INDEX
    Explanations

    java source code

    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
    வும்
    2.95
    রা
    2.77
    ย
    2.50
    ný
    2.48
     deter
    2.45
    Jetzt
    2.42
    ຍ
    2.42
    ని
    2.37
    ά
    2.37
    কর
    2.36
    POSITIVE LOGITS
    ்
    3.19
    на
    2.84
     cbind
    2.53
    uterine
    2.47
     curbs
    2.42
    forming
    2.33
    ي
    2.30
    et
    2.29
    frames
    2.25
    ेक्स
    2.24
    Activations Density 0.010%

    No Known Activations