© 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. 247509
    Prev
    Next
    INDEX
    Explanations

    sales volume, Labor Day, board up

    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
    дна
    0.49
     അതിന്റെ
    0.46
     демокра
    0.45
    收聽
    0.45
     расходов
    0.44
    ћ
    0.44
    Haupt
    0.44
    він
    0.44
    CONTAIN
    0.43
    ୪
    0.43
    POSITIVE LOGITS
     Khi
    0.53
     Wenn
    0.50
     Ham
    0.50
    <em>
    0.49
     or
    0.49
     Để
    0.49
     ($\
    0.49
     oder
    0.48
     alerted
    0.48
     Had
    0.48
    Activations Density 0.000%

    No Known Activations