© 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. 119861
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
    <0x0D>
    0.68
     immunized
    0.66
     Ein
    0.66
     theſe
    0.65
    </h4>
    0.63
     Anda
    0.62
     Een
    0.61
    </h1>
    0.59
    t
    0.59
    olok
    0.57
    POSITIVE LOGITS
    다
    0.84
     crest
    0.71
    די
    0.70
    이나
    0.66
     приме
    0.64
    வு
    0.63
    ון
    0.63
     구매
    0.63
     הוא
    0.63
    рал
    0.63
    Activations Density 0.000%

    No Known Activations