© 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. 69865
    Prev
    Next
    INDEX
    Explanations

    times and slots

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

    if you

    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
    icklabels
    0.39
     گوئیاں
    0.39
    었던
    0.38
    顱
    0.38
    하고자
    0.38
    انات
    0.38
    ová
    0.38
     корпу
    0.37
    瑚
    0.37
    ี้
    0.37
    POSITIVE LOGITS
     four
    0.51
     two
    0.49
     three
    0.47
     mainten
    0.47
     after
    0.46
     a
    0.46
     poems
    0.46
     when
    0.45
     $
    0.44
    six
    0.44
    Activations Density 0.001%

    No Known Activations