© 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. 222509
    Prev
    Next
    INDEX
    Explanations

    legal or financial evaluations

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

    accessing specific information

    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
     Среди
    0.50
    也能
    0.47
    ,...
    0.46
    prueba
    0.46
     Neander
    0.46
     洋
    0.45
     FDA
    0.45
     covalently
    0.44
     Ζ
    0.43
     Zelda
    0.43
    POSITIVE LOGITS
     Bewert
    0.43
    σιμοποι
    0.43
     valuations
    0.42
     signalled
    0.42
    ћи
    0.42
     قیادت
    0.41
    æld
    0.41
     myopia
    0.41
    defeat
    0.40
    ệng
    0.40
    Activations Density 0.000%

    No Known Activations