© 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. 158721
    Prev
    Next
    INDEX
    Explanations

    Acts (followed by legislative details)

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

    Sanskrit, atom, distance, updates

    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
     elephants
    0.46
     manu
    0.46
     nominated
    0.44
     esse
    0.43
     a
    0.42
     kerana
    0.42
    elephant
    0.41
    ↵
    0.41
     Esse
    0.41
     pyt
    0.41
    POSITIVE LOGITS
    ገኙ
    0.51
    敺
    0.51
    ուն
    0.50
    ંદ
    0.48
    ላቸው
    0.48
    গর্
    0.48
    제의
    0.48
    ूली
    0.47
    लिंग
    0.47
    ग्रेड
    0.47
    Activations Density 0.000%

    No Known Activations