© 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. 17881
    Prev
    Next
    INDEX
    Explanations

    road junctions and intersections

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

    valuable, code, premium, core

    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
     kř
    0.45
     teore
    0.44
     conduits
    0.43
     outfitted
    0.43
     anticor
    0.42
     ĝ
    0.42
     amélior
    0.42
     nécessairement
    0.41
     scalable
    0.41
     doux
    0.41
    POSITIVE LOGITS
    сон
    0.46
     없다
    0.46
     причина
    0.45
    ן
    0.45
    ктор
    0.44
     фигу
    0.44
    ಾಗ್
    0.44
    때
    0.43
    нд
    0.43
    рами
    0.43
    Activations Density 0.001%

    No Known Activations