© 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. 194231
    Prev
    Next
    INDEX
    Explanations

    you can

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

    technical details

    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
    롤
    0.52
    그
    0.51
     et
    0.50
     anhydride
    0.50
     anisotrop
    0.50
    uum
    0.49
     detainees
    0.48
     নেবার
    0.48
     disinterested
    0.48
     inquired
    0.48
    POSITIVE LOGITS
    {})
    0.45
    asText
    0.43
     mutlu
    0.43
    重要
    0.42
    恢复
    0.42
    ла
    0.42
    永
    0.42
    zt
    0.42
     ज़
    0.41
    吶
    0.41
    Activations Density 0.001%

    No Known Activations