© 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. 37267
    Prev
    Next
    INDEX
    Explanations

    foreign languages and technical terms

    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
    :
    0.48
     Greater
    0.47
     Lesser
    0.47
    は
    0.47
     Workspace
    0.46
     greater
    0.46
    2
    0.46
     citadel
    0.45
     semicircle
    0.45
     Z
    0.45
    POSITIVE LOGITS
    Dados
    0.52
    ConfigFiles
    0.52
    Kann
    0.49
    م
    0.49
    addena
    0.48
     fragen
    0.48
    دخل
    0.45
    د
    0.45
    𝙘
    0.45
    Todos
    0.45
    Activations Density 0.004%

    No Known Activations