© 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. 16836
    Prev
    Next
    INDEX
    Explanations

    state, progress, or timing

    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
     jähr
    0.46
     participaron
    0.43
     annuelle
    0.43
     გამოყენ
    0.43
     annually
    0.42
     jährlich
    0.42
     ઉપયોગ
    0.41
    늉
    0.41
    шлось
    0.40
     participó
    0.40
    POSITIVE LOGITS
     henüz
    0.63
     momentum
    0.63
     nearing
    0.62
     halfway
    0.61
     midway
    0.61
     아직
    0.61
     बढ़त
    0.60
    目前的
    0.58
    まだ
    0.58
     состояние
    0.58
    Activations Density 0.056%

    No Known Activations