© 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. 145904
    Prev
    Next
    INDEX
    Explanations

    ages for investment

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

    names and technical terms

    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
    iencing
    0.50
    িয়াছিলেন
    0.50
    ahili
    0.50
    eties
    0.49
    ਠ
    0.48
     players
    0.46
     suss
    0.46
    秫
    0.46
     cakes
    0.45
     gamers
    0.45
    POSITIVE LOGITS
    ص
    0.49
    citation
    0.45
    渉
    0.45
     Ivo
    0.44
     Direkt
    0.44
     Hé
    0.44
     أج
    0.44
     Sleeve
    0.43
    Link
    0.43
     Vie
    0.43
    Activations Density 0.000%

    No Known Activations