© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    penalty charge notice

    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
    IPAL
    0.39
    usine
    0.38
    ilage
    0.38
     ಕೆಲವು
    0.37
    楖
    0.37
    Inventory
    0.36
     tropomyosin
    0.36
    uvad
    0.36
     municipalité
    0.36
    經濟
    0.36
    POSITIVE LOGITS
     $('
    0.37
     sexuality
    0.36
     $*
    0.36
    ण्य
    0.35
     насо
    0.35
     sql
    0.35
     elong
    0.35
     elongate
    0.35
     excitation
    0.34
     đổ
    0.34
    Activations Density 0.001%

    No Known Activations