© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    assignments and structures

    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
    )،
    0.35
    ）」
    0.32
    幵
    0.31
    ،
    0.31
    »،
    0.28
    हरादून
    0.28
    )...
    0.27
    )....
    0.26
    ၊
    0.26
    髪
    0.26
    POSITIVE LOGITS
     none
    0.32
     None
    0.31
    NONE
    0.30
     reducing
    0.30
     чого
    0.29
     l
    0.29
     змен
    0.29
     nilai
    0.28
     x
    0.28
     LES
    0.28
    Activations Density 0.094%

    No Known Activations