© 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. 161598
    Prev
    Next
    INDEX
    Explanations

    birth, shots, walls, accidents

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

    movement and control interfaces

    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
    ザ
    0.50
    なる
    0.48
    дне
    0.47
    ส
    0.47
    徳
    0.46
    質な
    0.46
    雑誌
    0.46
    aptops
    0.45
    ๐
    0.45
    пла
    0.44
    POSITIVE LOGITS
     ruim
    0.55
     Bewegung
    0.54
     megt
    0.51
    ىز
    0.50
     Binding
    0.50
     lineups
    0.50
     Bedien
    0.50
     fea
    0.49
     Ihren
    0.48
     Amp
    0.48
    Activations Density 0.002%

    No Known Activations