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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48570
    Prev
    Next
    INDEX
    Explanations

    common phrases following specific words

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

    security, incentive, party, miner

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gioc
    0.47
     versiones
    0.46
     javac
    0.46
     scopes
    0.45
     mounts
    0.45
     ncol
    0.45
     pédagog
    0.45
     հ
    0.45
     geh
    0.45
     cognac
    0.45
    POSITIVE LOGITS
    出一
    0.42
    $^{
    0.41
    önes
    0.41
    example
    0.40
    ְ
    0.40
    調查
    0.40
    male
    0.39
    মার
    0.39
    是我
    0.39
    ÜR
    0.39
    Activations Density 0.000%

    No Known Activations