© 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. 241037
    Prev
    Next
    INDEX
    Explanations

    count of visits

    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
    у
    0.52
    ''
    0.47
    ‹
    0.45
     바라
    0.44
    <0x90>
    0.44
    г
    0.44
    ウ
    0.43
     볼
    0.43
     Ваши
    0.43
    ве
    0.42
    POSITIVE LOGITS
     amin
    0.45
    進行
    0.43
     یق
    0.43
     Penal
    0.42
    epad
    0.41
     nul
    0.41
    救援
    0.40
     vis
    0.40
     kesalahan
    0.39
     அழிக்க
    0.39
    Activations Density 0.007%

    No Known Activations