© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    questions and instructions

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

    Choose, solve, select, list

    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
    жий
    0.29
    ご飯
    0.28
     brainchild
    0.28
    売り
    0.27
    貓
    0.27
    َة
    0.27
     comércio
    0.27
    グッズ
    0.27
    さんも
    0.26
     thuyền
    0.26
    POSITIVE LOGITS
     Thinking
    0.31
     N
    0.30
    asa
    0.30
    rm
    0.29
    As
    0.29
     Help
    0.29
    umba
    0.29
     Choose
    0.29
     Which
    0.29
    umen
    0.29
    Activations Density 0.005%

    No Known Activations