© 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. 163513
    Prev
    Next
    INDEX
    Explanations

    international restrictions

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

    discharge / limitations

    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
    くなり
    0.54
     दूंगा
    0.52
    वर्ती
    0.52
    鋪
    0.50
    椇
    0.50
    ографи
    0.50
    ﹋
    0.50
    рал
    0.49
    ಬ್ಬಿಣ
    0.49
    дт
    0.49
    POSITIVE LOGITS
    lic
    0.48
    imo
    0.48
    ng
    0.46
    lices
    0.46
     buz
    0.46
    ice
    0.46
     can
    0.45
    ’
    0.44
    iece
    0.43
    lee
    0.43
    Activations Density 0.001%

    No Known Activations