© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14577
    Prev
    Next
    INDEX
    Explanations

    code, math, movie titles, history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     利
    1.48
    浦
    1.35
     ベッド
    1.30
     резер
    1.27
    ピー
    1.25
    栃木
    1.24
    ツール
    1.23
     ファッション
    1.23
    迅
    1.22
     余
    1.22
    POSITIVE LOGITS
     ele
    0.82
     list
    0.80
     mono
    0.77
     mam
    0.74
    stand
    0.74
    er
    0.73
     Yes
    0.71
    yes
    0.70
     de
    0.70
     Ellen
    0.69
    Activations Density 0.042%

    No Known Activations