© 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-65K
    7. 28041
    Prev
    Next
    INDEX
    Explanations

    specialized classifications

    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_65k_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
    ğini
    0.49
    மக்கள்
    0.49
     التس
    0.48
    ్యాచ్
    0.48
    合适的
    0.48
     చేసుకు
    0.48
     定义
    0.47
    仼
    0.47
     ಬೇ
    0.46
    បន្ថែម
    0.46
    POSITIVE LOGITS
    cog
    0.50
    h
    0.46
    r
    0.46
    Fract
    0.45
    nomin
    0.45
     cog
    0.45
    sg
    0.44
    itt
    0.44
    sc
    0.44
    DLC
    0.44
    Activations Density 0.012%

    No Known Activations