© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    dialogue markers and titles

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

    gentleman, sailor, limerick

    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
     aufgrund
    0.61
     meningkatkan
    0.60
     langfrist
    0.59
     dimensione
    0.58
     utilizzo
    0.58
     حجم
    0.57
     கட்டமை
    0.57
    棪
    0.57
     sustainably
    0.57
     supporto
    0.57
    POSITIVE LOGITS
     tavern
    0.57
     homely
    0.57
     waiter
    0.53
     gentleman
    0.52
     marrying
    0.51
     sailor
    0.50
     waistcoat
    0.50
     robbers
    0.50
     Cupid
    0.50
     saloon
    0.49
    Activations Density 0.025%

    No Known Activations