© 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. 16919
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs

    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
     compl
    0.46
    𝑎
    0.43
     fain
    0.41
    conexion
    0.41
     porttitor
    0.41
    ক্রম
    0.41
     flexion
    0.41
     darse
    0.40
     tuck
    0.40
     у
    0.40
    POSITIVE LOGITS
    
    0.48
    Mass
    0.44
    Hus
    0.43
    Priority
    0.39
     интенсив
    0.39
    utherland
    0.38
    لال
    0.38
    مان
    0.38
    短暂
    0.38
    ერ
    0.38
    Activations Density 0.000%

    No Known Activations