© 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. 17343
    Prev
    Next
    INDEX
    Explanations

    positional phrases

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

    diving into

    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
    _
    0.32
    ・
    0.31
    and
    0.29
    /
    0.29
    और
    0.29
    0.28
    {
    0.28
     மற்றும்
    0.27
     и
    0.27
    www
    0.27
    POSITIVE LOGITS
     vasculature
    0.28
     dwell
    0.27
     terhadap
    0.27
     buddhav
    0.27
     drivetrain
    0.26
     rapidity
    0.26
     thrombo
    0.26
    جموع
    0.26
     harmonies
    0.26
     revanche
    0.25
    Activations Density 0.000%

    No Known Activations