© 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. 43352
    Prev
    Next
    INDEX
    Explanations

    languages, heat, optimization

    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
    Imagen
    0.46
    ведите
    0.45
    መረ
    0.43
    事的
    0.43
    смо
    0.42
    Imagem
    0.41
    ве
    0.40
    द
    0.40
    τε
    0.40
    ຕົວ
    0.39
    POSITIVE LOGITS
     attraverso
    0.52
     erhältlich
    0.49
     vuol
    0.47
    ഓം
    0.47
     lavori
    0.46
     através
    0.45
     ഊ
    0.45
    UIApplication
    0.45
     Regeln
    0.44
     brzo
    0.44
    Activations Density 0.002%

    No Known Activations