© 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. 175531
    Prev
    Next
    INDEX
    Explanations

    see or hear about

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

    gauge market

    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
    eonium
    0.45
    hock
    0.43
    рованных
    0.43
    hman
    0.42
     bebés
    0.41
    ፐ
    0.40
     الب
    0.39
    projectView
    0.39
     женщин
    0.39
     Дуб
    0.38
    POSITIVE LOGITS
    ስ
    0.47
    Ends
    0.45
    Determ
    0.45
    Teller
    0.45
    斃
    0.45
     azy
    0.44
    ס
    0.44
    WeekDates
    0.43
    figuration
    0.43
    Differ
    0.42
    Activations Density 0.001%

    No Known Activations