© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35916
    Prev
    Next
    INDEX
    Explanations

    list items and section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     విషయం
    0.38
    ุป
    0.37
     curves
    0.35
     Franken
    0.35
    ATER
    0.34
     habitat
    0.33
    <0xAB>
    0.33
    奈
    0.33
     sponges
    0.32
     hydro
    0.32
    POSITIVE LOGITS
     tidak
    0.49
     gründ
    0.47
     создает
    0.46
    தம்ப
    0.45
    otherwise
    0.44
     womenProduct
    0.44
     Tidak
    0.44
     ምር
    0.43
     nicht
    0.43
    推出了
    0.43
    Activations Density 0.129%

    No Known Activations