© 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. 111512
    Prev
    Next
    INDEX
    Explanations

    availability of resources

    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
     nosotros
    0.53
    ш
    0.51
    anud
    0.50
    anek
    0.48
    이사
    0.47
    ю
    0.47
    
    0.47
    
    0.47
    zhong
    0.46
     בי
    0.46
    POSITIVE LOGITS
    H
    0.58
    K
    0.50
    ML
    0.46
     détecter
    0.45
    V
    0.45
    X
    0.44
     finder
    0.43
    mc
    0.43
    mis
    0.43
     Chrome
    0.43
    Activations Density 0.002%

    No Known Activations