© 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. 131270
    Prev
    Next
    INDEX
    Explanations

    running benchmarks and award winners

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

    story generation

    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
    ੱਕ
    0.46
     vaccinations
    0.45
    潛行
    0.44
     meestal
    0.44
    干燥
    0.44
    ᓃ
    0.43
    נים
    0.43
     방향
    0.43
    狞
    0.43
     நிறைய
    0.42
    POSITIVE LOGITS
     ग्रेट
    0.54
    ্টের
    0.54
    later
    0.48
    ed
    0.47
     элемента
    0.46
    prnewswire
    0.46
    arial
    0.46
    eric
    0.46
     pulled
    0.46
    crown
    0.46
    Activations Density 0.000%

    No Known Activations