© 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. 232770
    Prev
    Next
    INDEX
    Explanations

    found in, of, to, that, I

    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
    </h2>
    0.49
    0
    0.48
     of
    0.47
     retribution
    0.45
    falls
    0.44
    ص
    0.44
     TS
    0.44
     OF
    0.44
     OFW
    0.43
    initis
    0.43
    POSITIVE LOGITS
    Anche
    0.58
    ΑΣ
    0.57
    ISING
    0.55
     rilas
    0.52
    डली
    0.49
     νέ
    0.49
    আমিন
    0.49
     versiones
    0.49
     mehrerer
    0.48
     aprile
    0.48
    Activations Density 0.001%

    No Known Activations