© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    technical concepts and analysis

    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
    कायदा
    0.52
     সেটা
    0.46
     entusiasmo
    0.45
    politik
    0.45
    满满
    0.44
     unapolog
    0.44
    尷
    0.43
     ప్రేక్షకు
    0.42
     अपराध
    0.42
     แถม
    0.42
    POSITIVE LOGITS
     during
    0.61
    。
    0.54
    .
    0.54
     between
    0.52
    during
    0.51
    ↵
    0.50
    、
    0.48
     when
    0.48
    when
    0.48
     after
    0.46
    Activations Density 0.122%

    No Known Activations