© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    names and 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
     Martin
    0.48
    ص
    0.44
     Rose
    0.43
     रोहित
    0.43
     Rachel
    0.43
     Elizabeth
    0.42
     Rebecca
    0.42
     Gavin
    0.42
     Jennifer
    0.41
     Michael
    0.41
    POSITIVE LOGITS
    รูป
    0.36
     ตาย
    0.35
    以前
    0.35
    眺
    0.34
    なければ
    0.33
    Soviet
    0.33
     СССР
    0.32
    ก็
    0.32
    กฎ
    0.32
    ដូច្ន
    0.32
    Activations Density 0.000%

    No Known Activations