© 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. 19803
    Prev
    Next
    INDEX
    Explanations

    tabular data headers

    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
    ।
    0.77
     an
    0.72
    an
    0.70
     나가
    0.65
    it
    0.64
    >∕</
    0.64
     ਬ
    0.64
     않을
    0.64
    ਰ
    0.64
    钀
    0.64
    POSITIVE LOGITS
    1
    1.01
    2
    0.95
    6
    0.94
    5
    0.89
    4
    0.82
    7
    0.80
    '
    0.79
    3
    0.76
    ك
    0.75
    די
    0.69
    Activations Density 0.002%

    No Known Activations