© 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-16K
    7. 13513
    Prev
    Next
    INDEX
    Explanations

    multiplied by itself

    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_16k_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
     کردن
    0.43
     अला
    0.40
    டுகளை
    0.39
    🅻
    0.39
    uetooth
    0.39
    )}>
    0.38
     direccion
    0.38
     alight
    0.38
     operación
    0.38
     زین
    0.38
    POSITIVE LOGITS
    사회
    0.40
     সামাজিক
    0.39
    পর
    0.38
     piacere
    0.37
    न्या
    0.37
    纰
    0.37
     वा
    0.36
    ष
    0.35
    返回
    0.34
     skj
    0.34
    Activations Density 0.008%

    No Known Activations