© 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. 7552
    Prev
    Next
    INDEX
    Explanations

    kinds of, addition, and

    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
     shredded
    0.33
     oversaw
    0.31
     hiked
    0.31
     ₽
    0.31
     hosted
    0.31
     தற்போது
    0.30
     wacky
    0.30
    ቑ
    0.30
     optimised
    0.30
     hasn
    0.30
    POSITIVE LOGITS
     मनुष्य
    0.36
     인간
    0.34
     Comparative
    0.33
     अध्याय
    0.32
     челове
    0.31
    संबंध
    0.31
    chapter
    0.30
     Chapter
    0.30
     물질
    0.30
     গ্রন্থে
    0.29
    Activations Density 0.047%

    No Known Activations