© 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. 111591
    Prev
    Next
    INDEX
    Explanations

    questions, possibilities, server

    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
     pensar
    0.54
     ដ
    0.51
     política
    0.51
     administrativas
    0.49
     思い
    0.49
     перший
    0.48
     fraude
    0.46
     Сейчас
    0.46
     hablan
    0.46
    ಪಟ್ಟ
    0.46
    POSITIVE LOGITS
     Chemists
    0.46
     машиналары
    0.45
    ’)
    0.44
    nPortIndex
    0.43
     Ultrasonic
    0.43
    ’
    0.43
    ocycl
    0.42
     amusement
    0.41
    érons
    0.41
     photons
    0.41
    Activations Density 0.003%

    No Known Activations