© 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. 217522
    Prev
    Next
    INDEX
    Explanations

    alternative outcomes and actions

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

    SAP solutions

    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
    ای
    0.50
    номет
    0.49
     Paytm
    0.48
     الله
    0.47
    ۴
    0.46
    🍃
    0.46
     بانک
    0.46
    😓
    0.46
    ۱
    0.46
    💦
    0.46
    POSITIVE LOGITS
    ser
    0.45
    erving
    0.44
    los
    0.43
    ená
    0.43
    獠
    0.43
    iquer
    0.43
    欴
    0.42
    gli
    0.42
    鵠
    0.41
    ʢ
    0.41
    Activations Density 0.001%

    No Known Activations