© 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. 29934
    Prev
    Next
    INDEX
    Explanations

    mention specific word/phrase

    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
     {
    0.41
     perd
    0.41
     cilia
    0.41
     palettes
    0.40
     carb
    0.39
     لان
    0.38
     palette
    0.37
     deple
    0.37
     nut
    0.36
     $
    0.36
    POSITIVE LOGITS
     succinctly
    0.46
     criticised
    0.42
     користу
    0.41
    वाधिकार
    0.41
    uiscono
    0.41
     пользова
    0.40
    शब्द
    0.39
    ুকে
    0.39
     जनरल
    0.38
    读者
    0.38
    Activations Density 0.000%

    No Known Activations