© 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. 25525
    Prev
    Next
    INDEX
    Explanations

    "it", "name", "a", "figures"

    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
    动
    0.45
     not
    0.43
     Marine
    0.42
    เส
    0.42
    voice
    0.40
    (
    0.40
    ุ
    0.40
    อน
    0.39
    孤
    0.39
    ον
    0.39
    POSITIVE LOGITS
     теория
    0.54
     consideramos
    0.48
     срок
    0.47
     conceitos
    0.47
     teoría
    0.47
     involunt
    0.47
     පේශ
    0.47
    ⭕
    0.46
     conceito
    0.46
     Körper
    0.46
    Activations Density 0.000%

    No Known Activations