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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31189
    Prev
    Next
    INDEX
    Explanations

    verifying correctness

    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
     for
    0.66
    \
    0.62
    ti
    0.61
     purport
    0.61
    t
    0.59
     One
    0.59
     ON
    0.58
     arid
    0.58
    se
    0.56
     G
    0.55
    POSITIVE LOGITS
    ниці
    0.70
    ство
    0.65
    но
    0.64
    ა
    0.63
    сон
    0.61
    能
    0.61
    にっいて
    0.59
    ್ಣ
    0.59
    و
    0.59
    я
    0.59
    Activations Density 0.007%

    No Known Activations