© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    centrality and core concepts

    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
    ق
    0.82
    ল
    0.77
    ק
    0.73
    ك
    0.68
    ור
    0.66
    ని
    0.65
    هم
    0.65
    ص
    0.65
     subclasses
    0.60
    ל
    0.60
    POSITIVE LOGITS
     centrale
    1.12
     center
    1.09
     central
    1.09
    central
    1.09
     центра
    1.08
     центр
    1.08
     centre
    1.07
    Center
    1.07
     中心
    1.06
     centro
    1.04
    Activations Density 0.051%

    No Known Activations