© 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. 135697
    Prev
    Next
    INDEX
    Explanations

    www, ., !, %

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

    accuracy and evidence

    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
    あ
    0.48
    یرو
    0.46
     shew
    0.45
    ませんでした
    0.44
    ה
    0.43
     le
    0.43
    כם
    0.42
     k
    0.42
    你有
    0.42
     y
    0.42
    POSITIVE LOGITS
     bilingual
    0.51
    atives
    0.50
    otts
    0.48
     थर
    0.48
    itimes
    0.48
    ished
    0.48
    áln
    0.48
    iches
    0.47
    íveis
    0.46
    ishes
    0.46
    Activations Density 0.000%

    No Known Activations