© 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. 173212
    Prev
    Next
    INDEX
    Explanations

    until _

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

    subject followed by verb

    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
    2
    0.55
     \
    0.54
    <0x0D>
    0.53
    ↵
    0.51
    Fluid
    0.50
    makers
    0.48
    s
    0.47
    parents
    0.47
    ;;
    0.46
     Fluids
    0.46
    POSITIVE LOGITS
    閁
    0.54
    荩
    0.51
     দক্ষতা
    0.50
     perjury
    0.50
     damal
    0.50
     Пі
    0.49
    當時
    0.49
     দেরি
    0.49
     weinig
    0.49
     densité
    0.48
    Activations Density 0.001%

    No Known Activations