© 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. 196882
    Prev
    Next
    INDEX
    Explanations

    diameter, %, 58%

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

    editing and transformation

    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
    일을
    0.47
    Ẫ
    0.45
    лья
    0.43
     policeman
    0.43
    진다
    0.43
     policemen
    0.43
    न्
    0.42
     threaten
    0.41
    אין
    0.41
    진
    0.41
    POSITIVE LOGITS
     संपादित
    0.58
     संपाद
    0.53
    uf
    0.52
     संपादक
    0.50
    hiyam
    0.49
    metadata
    0.48
     कले
    0.48
    subseteq
    0.48
    ice
    0.47
     بهبود
    0.47
    Activations Density 0.000%

    No Known Activations