© 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. 168768
    Prev
    Next
    INDEX
    Explanations

    file or example

    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
     hemp
    0.44
     Be
    0.42
    补充
    0.42
    达
    0.42
     démarrage
    0.40
    內
    0.40
    内
    0.39
    签
    0.38
     Turbo
    0.38
    为主
    0.38
    POSITIVE LOGITS
    oshape
    0.51
    ornos
    0.51
     automóviles
    0.50
    wijk
    0.49
     biliary
    0.48
     geométricas
    0.48
     количе
    0.47
    リズム
    0.47
     assays
    0.47
    rifle
    0.46
    Activations Density 0.010%

    No Known Activations