© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    proverbs and adages

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

    idioms, riddles, and wordplay

    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
     resists
    0.47
     simonsen
    0.42
    挔
    0.42
    णाल
    0.42
     asist
    0.41
     broadband
    0.41
     explosions
    0.41
     planen
    0.41
     connectors
    0.40
    助理
    0.40
    POSITIVE LOGITS
     proverb
    1.27
     adage
    1.20
     proverbial
    1.04
    谚
    0.97
    諺
    0.91
     Proverbs
    0.88
     phrase
    0.86
     cliché
    0.84
     cliche
    0.82
    Phrase
    0.80
    Activations Density 0.154%

    No Known Activations