© 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. 131926
    Prev
    Next
    INDEX
    Explanations

    program, salad, special, jobs, IRA, companies, general

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

    historical context or philosophical arguments

    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
     visually
    0.47
     Consol
    0.46
    ✅
    0.45
     shaded
    0.44
     (\%)
    0.43
     Cups
    0.43
     gráficos
    0.43
     SVG
    0.42
     /
    0.42
    ٰذا
    0.42
    POSITIVE LOGITS
     pledging
    0.48
    斯特
    0.47
    ករ
    0.47
     projets
    0.46
    terrorism
    0.46
     naszych
    0.45
     formulating
    0.45
     паліты
    0.45
    ур
    0.42
     formulations
    0.42
    Activations Density 0.000%

    No Known Activations