© 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. 196494
    Prev
    Next
    INDEX
    Explanations

    international script or symbols

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

    realistic conclusion

    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
     ধীরে
    0.49
    otras
    0.48
     ”
    0.46
     died
    0.45
     slowly
    0.45
    undang
    0.44
     venturing
    0.44
     overcrowding
    0.44
     mentality
    0.44
     Buckley
    0.43
    POSITIVE LOGITS
    ΟΥ
    0.55
    ন
    0.54
    зм
    0.53
    יש
    0.51
    ن
    0.51
    Съ
    0.50
    ഓം
    0.50
    ঞ
    0.50
    ס
    0.50
    سن
    0.49
    Activations Density 0.000%

    No Known Activations