© 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. 223330
    Prev
    Next
    INDEX
    Explanations

    waterproofing and prediction

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

    capture wanted it

    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
     confi
    0.56
    бур
    0.52
    нів
    0.51
    ἃ
    0.51
     invented
    0.50
    тальян
    0.49
    ﮐ
    0.48
     encomendas
    0.47
    普
    0.47
     calibrated
    0.47
    POSITIVE LOGITS
     करनाल
    0.51
     ระบบ
    0.50
    dam
    0.48
    to
    0.47
    below
    0.47
    loid
    0.46
    zoek
    0.46
     대상으로
    0.46
     नये
    0.45
    holder
    0.45
    Activations Density 0.002%

    No Known Activations