© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    listing, conjunctions, however

    np_acts-logits-general · gemini-2.5-flash-lite

    alternatives or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.74
    \
    0.67
    :
    0.63
     that
    0.63
    ：
    0.62
    ："
    0.59
    (
    0.58
    л
    0.58
    ב
    0.54
    يل
    0.53
    POSITIVE LOGITS
     तसेच
    0.73
    也就是说
    0.72
     تاہم
    0.71
    however
    0.71
     چنانچہ
    0.66
     همچنین
    0.63
     asimismo
    0.63
     however
    0.62
    -)
    0.62
     inoltre
    0.62
    Activations Density 0.149%

    No Known Activations