Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 232
    Prev
    Next
    INDEX
    Explanations

    usually, generally, always, often

    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
    使用了
    0.49
     ఉపయోగ
    0.49
     použ
    0.46
     ব্যবহার
    0.45
    了他的
    0.44
     Metadata
    0.42
     χρήση
    0.42
    郫
    0.42
     使用
    0.41
    infoHeader
    0.40
    POSITIVE LOGITS
     genellikle
    0.78
     usually
    0.77
     generally
    0.77
     always
    0.73
     geralmente
    0.73
     siempre
    0.71
     generalmente
    0.71
     अक्सर
    0.68
     cenderung
    0.68
     suele
    0.67
    Activations Density 0.079%

    No Known Activations