© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186985
    Prev
    Next
    INDEX
    Explanations

    pairs of tokens

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

    to analyze or remember

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    尸
    0.46
     $*$
    0.45
    ছার
    0.44
     proz
    0.44
     *:
    0.44
     BIB
    0.43
     Bich
    0.41
     lager
    0.41
     tapas
    0.41
     Salmonella
    0.41
    POSITIVE LOGITS
    เพื่อ
    0.55
     เพื่อ
    0.54
     председа
    0.50
    า
    0.50
    }\!\
    0.47
     рок
    0.47
     желание
    0.46
     अर्थात्
    0.46
     намере
    0.46
    editText
    0.46
    Activations Density 0.001%

    No Known Activations