© 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. 106135
    Prev
    Next
    INDEX
    Explanations

    physical therapy

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

    IP addresses and APIs

    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
     antique
    0.50
    ondan
    0.46
     kanker
    0.44
     adaptive
    0.42
    荞
    0.42
    nahmen
    0.42
     чему
    0.41
    edinte
    0.41
     웨
    0.41
     immagin
    0.41
    POSITIVE LOGITS
     ましょう
    0.57
     फटाफट
    0.51
     单位
    0.50
    lapse
    0.50
    可能会
    0.49
    കളും
    0.47
     তাড়াতাড়ি
    0.46
    可能會
    0.46
     remettre
    0.46
     Minaj
    0.46
    Activations Density 0.000%

    No Known Activations