© 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. 38614
    Prev
    Next
    INDEX
    Explanations

    margins and measurements

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

    latex margin settings

    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
    version
    0.43
    intensity
    0.43
    nearly
    0.41
    scale
    0.40
     TextAlign
    0.40
     scale
    0.39
    text
    0.38
    ْن
    0.38
    Version
    0.38
    negative
    0.37
    POSITIVE LOGITS
     dissolves
    0.47
    颈
    0.46
     regulates
    0.45
     позволит
    0.43
     вещества
    0.42
    萆
    0.42
    ➫
    0.42
     ሶ
    0.42
     Кы
    0.41
     изго
    0.41
    Activations Density 0.000%

    No Known Activations