© 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. 116248
    Prev
    Next
    INDEX
    Explanations

    you will love

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

    **bootstrap** samples

    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
    Sp
    0.57
    UN
    0.55
    UM
    0.55
    UK
    0.53
    UC
    0.52
    。
    0.51
    Um
    0.50
    function
    0.49
    NT
    0.49
    //
    0.49
    POSITIVE LOGITS
     Flight
    0.52
    supportsFocus
    0.49
    bindingFields
    0.47
    ضة
    0.47
    elevationMap
    0.46
     ফ্লাইট
    0.45
     Slav
    0.44
    $\--
    0.44
     adhipp
    0.43
     கத
    0.43
    Activations Density 0.001%

    No Known Activations