© 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. 191293
    Prev
    Next
    INDEX
    Explanations

    Rachmaninoff, rachitic

    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
     ball
    0.42
    rase
    0.41
    ﺭ
    0.39
    tender
    0.38
    Ras
    0.38
     التن
    0.38
     bowls
    0.36
    Organisation
    0.36
    球
    0.35
    Background
    0.35
    POSITIVE LOGITS
     Dodson
    0.40
     Lloyd
    0.39
     Jet
    0.37
     laz
    0.37
     Play
    0.36
     кто
    0.36
     Polda
    0.36
     translucent
    0.35
     Poy
    0.35
     Julie
    0.35
    Activations Density 0.005%

    No Known Activations