© 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. 181226
    Prev
    Next
    INDEX
    Explanations

    geometric concepts and numbers

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

    * operations followed by result

    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
    গীর
    0.40
     *)(
    0.39
    以下
    0.38
     және
    0.38
    ），
    0.38
    jalan
    0.38
    indahan
    0.37
    考虑到
    0.37
    可能
    0.36
     士
    0.36
    POSITIVE LOGITS
    ៕
    0.44
    淍
    0.39
    当時の
    0.38
     Psal
    0.36
     مذکور
    0.36
    るので
    0.35
     damals
    0.35
     Rabat
    0.35
    ومة
    0.35
     بالله
    0.34
    Activations Density 0.001%

    No Known Activations