© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 177796
    Prev
    Next
    INDEX
    Explanations

    election, flyers, rent, corridor, aperture

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

    body image, earned rewards, who's picking up, stellate ganglion, £10 note, included a bridge, deviated septum, what's up bro, all the people

    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
     үчүн
    0.48
    iteracy
    0.45
    ルダー
    0.43
    czyny
    0.43
    ナ
    0.43
    マックス
    0.42
    フルーツ
    0.42
    ミュージ
    0.41
    エム
    0.41
    培训
    0.41
    POSITIVE LOGITS
    ^{*}(
    0.52
    ^{+}
    0.50
    ajero
    0.49
    )+
    0.48
    )}{
    0.48
     جائے
    0.48
     d
    0.47
     nitric
    0.46
     শর
    0.46
     g
    0.46
    Activations Density 0.001%

    No Known Activations