© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103801
    Prev
    Next
    INDEX
    Explanations

    Silmaril Melian

    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_16_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
    dincer
    0.60
     rejoice
    0.57
     ш
    0.57
     Rfe
    0.56
     потому
    0.56
     dễ
    0.55
     පො
    0.54
    ﺔ
    0.54
     Issled
    0.54
    abung
    0.53
    POSITIVE LOGITS
    ون
    0.54
    مل
    0.53
    ز
    0.53
    ва
    0.53
     (
    0.52
    ט
    0.52
    ைகள்
    0.50
    ουν
    0.50
    ג
    0.49
    جل
    0.49
    Activations Density 0.001%

    No Known Activations