© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20933
    Prev
    Next
    INDEX
    Explanations

    howhowhow it works

    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_40_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
     тих
    0.40
     valueForKey
    0.39
    <unused86>
    0.38
     టిప్పు
    0.37
     остается
    0.37
    uen
    0.37
     toets
    0.36
    iteten
    0.36
     daarna
    0.35
     Crystallogr
    0.34
    POSITIVE LOGITS
     paints
    0.40
     fata
    0.39
    澈
    0.39
    input
    0.38
     bandes
    0.38
    JsonResponse
    0.38
    Ꮴ
    0.38
     patrón
    0.38
     сфе
    0.37
     Trails
    0.37
    Activations Density 0.000%

    No Known Activations