© 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. 50655
    Prev
    Next
    INDEX
    Explanations

    predict, clinging, primarily

    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
    िंग
    0.46
     преступ
    0.44
     ফ্ল
    0.43
    ishing
    0.41
    IME
    0.41
    
    0.40
     ሁ
    0.40
    梫
    0.40
    犯罪
    0.39
    혁
    0.39
    POSITIVE LOGITS
     પાણી
    0.50
     eases
    0.46
     locations
    0.46
     silica
    0.45
     parties
    0.44
     seats
    0.44
     disgust
    0.44
     punctured
    0.44
     o
    0.43
     don
    0.42
    Activations Density 0.001%

    No Known Activations