© 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. 143571
    Prev
    Next
    INDEX
    Explanations

    truly special

    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
     सैम
    0.48
    йон
    0.45
     cycled
    0.44
    е
    0.44
    ého
    0.43
     rô
    0.42
     ventilated
    0.42
    😅
    0.42
     pored
    0.41
     hearty
    0.41
    POSITIVE LOGITS
    Education
    0.50
    EDUCATION
    0.49
    マーク
    0.48
    Platz
    0.48
    紀錄
    0.46
    Mbps
    0.46
    Piece
    0.45
     মূলত
    0.45
    S
    0.45
    Pro
    0.45
    Activations Density 0.001%

    No Known Activations