© 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. 144028
    Prev
    Next
    INDEX
    Explanations

    in-memory data structures

    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
    urar
    0.46
    ridium
    0.43
     halus
    0.42
     голосо
    0.41
    orithm
    0.41
    ':'
    0.40
     دارید
    0.40
     blended
    0.40
    äns
    0.40
     निः
    0.39
    POSITIVE LOGITS
    Dep
    0.54
     godz
    0.52
    Coordinate
    0.50
    াহিয়ার
    0.48
    DepartTime
    0.48
    ሟ
    0.47
    מ
    0.47
    מח
    0.46
    أ
    0.46
     commune
    0.46
    Activations Density 0.000%

    No Known Activations