© 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. 41052
    Prev
    Next
    INDEX
    Explanations

    functions, models, spatial

    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
    ༽
    0.52
     ሁለት
    0.52
     மூன்று
    0.52
     ಮ
    0.51
    kring
    0.51
     இன்று
    0.51
     トリ
    0.51
    ᱑
    0.51
    𝚖
    0.51
     ಹೊಸ
    0.50
    POSITIVE LOGITS
     mayor
    0.50
     I
    0.49
    ,
    0.44
     “
    0.43
     artwork
    0.43
     arte
    0.43
     Mayor
    0.43
     May
    0.42
     Motion
    0.40
     stave
    0.39
    Activations Density 0.008%

    No Known Activations