© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19822
    Prev
    Next
    INDEX
    Explanations

    modelmodel sizes

    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_16_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
    1
    0.57
     .
    0.55
    drama
    0.52
    end
    0.51
    d
    0.51
    ام
    0.50
    g
    0.50
    ات
    0.50
    تنا
    0.50
    ོས་
    0.50
    POSITIVE LOGITS
     desviación
    0.51
     cách
    0.50
     hü
    0.50
     образу
    0.50
     annotate
    0.49
     заяви
    0.49
     auft
    0.48
     écriv
    0.48
     ដ
    0.48
     تَ
    0.48
    Activations Density 0.000%

    No Known Activations