© 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. 138725
    Prev
    Next
    INDEX
    Explanations

    JSON or API instructions

    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
    น
    0.52
    可愛い
    0.51
     좋아
    0.45
    n
    0.45
    unakan
    0.44
    ն
    0.44
    wonderful
    0.43
     पेंशन
    0.43
    ва
    0.43
    Line
    0.41
    POSITIVE LOGITS
     पीड़िता
    0.46
    <unused252>
    0.42
    <unused662>
    0.41
     hurricanes
    0.41
     resumed
    0.41
     mumbled
    0.41
    ulier
    0.41
     അല്ലെങ്കിൽ
    0.41
     aforementioned
    0.40
     sobbing
    0.40
    Activations Density 0.007%

    No Known Activations