© 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. 147
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    numbers and ordinal suffixes

    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
     stagn
    0.25
    ：（
    0.23
     deterior
    0.23
    =/
    0.23
     say
    0.23
    }:=\
    0.22
     prompt
    0.22
     pron
    0.22
     sit
    0.22
     enquire
    0.22
    POSITIVE LOGITS
     Sevent
    0.26
     Bắc
    0.26
     मील
    0.26
    莺
    0.26
    岁的
    0.26
     Hadley
    0.26
     Grammy
    0.25
    
    0.25
    ый
    0.25
     fundación
    0.25
    Activations Density 0.486%

    No Known Activations