© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15649
    Prev
    Next
    INDEX
    Explanations

    Washington personally, judgment ("

    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
    รายละเอียด
    0.41
    igheid
    0.41
    த்தினை
    0.41
    acija
    0.41
     उनसे
    0.41
    叽
    0.40
    但是在
    0.40
     уважа
    0.40
     زمانہ
    0.40
    ग़
    0.39
    POSITIVE LOGITS
    5
    0.46
     flights
    0.46
     infl
    0.43
     sensor
    0.43
     fibrin
    0.40
     calcium
    0.40
     tunnels
    0.40
     thermal
    0.40
     iodine
    0.40
     animals
    0.39
    Activations Density 0.003%

    No Known Activations