© 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. 134874
    Prev
    Next
    INDEX
    Explanations

    still hear

    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
     kategorii
    0.46
     войны
    0.45
     prawie
    0.43
    寥
    0.42
    了吧
    0.42
    了嗎
    0.42
    Images
    0.41
    了吗
    0.41
    なども
    0.41
    战争
    0.41
    POSITIVE LOGITS
     sitting
    0.50
     estando
    0.50
     앉
    0.49
     Sitting
    0.48
     añ
    0.48
     العص
    0.47
     Deve
    0.47
     handkerchief
    0.47
    َّ
    0.46
     jacuzzi
    0.46
    Activations Density 0.001%

    No Known Activations