© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42695
    Prev
    Next
    INDEX
    Explanations

    recognize and patterns

    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
     conseguir
    0.64
     設計
    0.64
    ﺭ
    0.63
    u
    0.60
    im
    0.59
     calcular
    0.59
     voltar
    0.59
    东西
    0.58
    kör
    0.58
    rs
    0.57
    POSITIVE LOGITS
    Recognition
    0.86
     recogn
    0.85
     reconoce
    0.80
    ם
    0.80
     Recognition
    0.79
    н
    0.77
     reconhe
    0.76
     recognition
    0.75
     recognize
    0.75
     recognized
    0.71
    Activations Density 0.052%

    No Known Activations