© 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. 231941
    Prev
    Next
    INDEX
    Explanations

    married names and dates

    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
    enas
    0.55
    }_{(
    0.49
    🤌
    0.47
    y
    0.47
    фы
    0.46
    eb
    0.45
    вай
    0.45
    runs
    0.45
    adays
    0.45
    🗻
    0.45
    POSITIVE LOGITS
     irrigation
    0.50
     cutters
    0.44
    的热
    0.44
     اﻻ
    0.42
     arabe
    0.42
     trapping
    0.42
     얘기
    0.41
     welder
    0.41
     espresso
    0.41
     Arab
    0.40
    Activations Density 0.001%

    No Known Activations