© 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. 150833
    Prev
    Next
    INDEX
    Explanations

    from phrases

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

    buttermilk, forging, exe

    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
    ﻴ
    0.49
    лик
    0.48
     passive
    0.44
    ="
    0.42
     demur
    0.42
    こ
    0.42
    いい
    0.42
    送り
    0.42
    لیم
    0.42
    滞
    0.42
    POSITIVE LOGITS
    hatiti
    0.54
     মুহুর
    0.51
     acquires
    0.50
    asida
    0.50
     Ankara
    0.49
    zovaniyu
    0.49
    itmen
    0.49
    م
    0.49
     arranges
    0.49
    ნ
    0.49
    Activations Density 0.000%

    No Known Activations