© 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. 228915
    Prev
    Next
    INDEX
    Explanations

    ports, Germany, deals, gateways

    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
     মেডিক্যাল
    0.52
    führ
    0.46
    Lin
    0.46
    Removal
    0.46
    Shi
    0.45
    🩺
    0.45
    Fir
    0.45
    âr
    0.44
    ੯
    0.44
    Re
    0.44
    POSITIVE LOGITS
     subtleties
    0.52
     sockets
    0.48
     formalities
    0.48
     lonely
    0.45
     have
    0.44
     locate
    0.44
     embryonic
    0.44
     precon
    0.43
     prospects
    0.43
     clichés
    0.43
    Activations Density 0.001%

    No Known Activations