© 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. 113038
    Prev
    Next
    INDEX
    Explanations

    explaining information or concepts

    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
     cancelar
    0.47
     квартира
    0.45
    zać
    0.44
     carga
    0.43
     Reactive
    0.43
    ˃
    0.41
    我
    0.41
    泰
    0.40
     ant
    0.40
    OPH
    0.40
    POSITIVE LOGITS
     عزی
    0.47
     علاوه
    0.46
     السيا
    0.46
     چندین
    0.44
     연결
    0.44
    lineContainer
    0.43
     لاکھ
    0.43
     برخی
    0.43
     파일을
    0.43
     suatu
    0.42
    Activations Density 0.003%

    No Known Activations