© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12485
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and logging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    假设
    0.54
    笂
    0.53
    首先
    0.52
    ศึก
    0.52
     aiutare
    0.52
    丙基
    0.52
     pede
    0.52
    视图
    0.51
     quidem
    0.51
     ಬಂಧ
    0.50
    POSITIVE LOGITS
     Wilkinson
    0.60
     tanh
    0.57
    ﻂ
    0.56
     Wig
    0.56
    どちら
    0.55
     kWh
    0.53
     Paran
    0.53
     Besitz
    0.53
     Precision
    0.53
     Wies
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.