© 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. 88103
    Prev
    Next
    INDEX
    Explanations

    additional administrative

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

    save Scene

    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
    ↵↵
    0.57
    </strong>
    0.52
    </u>
    0.49
     substr
    0.45
     Video
    0.45
    </em>
    0.44
    </h4>
    0.43
    เหตุ
    0.43
    긁
    0.42
     περισσότε
    0.42
    POSITIVE LOGITS
     tồn
    0.48
     округа
    0.48
    iado
    0.46
     انصاف
    0.46
    borders
    0.46
    nics
    0.46
    ukat
    0.46
     занима
    0.45
     llevaron
    0.45
    adá
    0.45
    Activations Density 0.001%

    No Known Activations