© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9198
    Prev
    Next
    INDEX
    Explanations

    minimum

    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_16_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
    ன்
    0.65
     attaqu
    0.64
     NTFS
    0.63
    น
    0.63
    ~(\
    0.62
     de
    0.62
    ーション
    0.62
    ^*\
    0.62
    ห
    0.61
    П
    0.61
    POSITIVE LOGITS
    at
    1.06
    3
    0.94
    Minimum
    0.78
    ний
    0.77
    า
    0.75
    as
    0.72
    4
    0.68
    UT
    0.66
    link
    0.66
    minimum
    0.66
    Activations Density 0.005%

    No Known Activations