© 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. 103888
    Prev
    Next
    INDEX
    Explanations

    selective emphasis, memory, evidence

    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
     has
    0.88
     is
    0.83
     a
    0.82
     was
    0.80
     बढ़ते
    0.79
     (
    0.78
     i
    0.76
     o
    0.76
     y
    0.76
    to
    0.76
    POSITIVE LOGITS
     selectively
    0.81
    Selective
    0.79
    د
    0.73
    ه
    0.73
     Selective
    0.68
     selective
    0.67
    breaker
    0.66
    ز
    0.65
    狀
    0.65
    دى
    0.63
    Activations Density 0.003%

    No Known Activations