© 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. 209735
    Prev
    Next
    INDEX
    Explanations

    authentication system interface

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

    examples, if, popular

    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
    /*
    0.49
    Als
    0.49
    ن
    0.48
    ን
    0.46
    ని
    0.46
    보
    0.46
     startups
    0.45
    الك
    0.45
    К
    0.44
    투
    0.44
    POSITIVE LOGITS
     quadrature
    0.47
     costitu
    0.46
     determinado
    0.45
     hydrological
    0.45
     commandBuffer
    0.44
     manipular
    0.44
     canoe
    0.43
     dune
    0.43
     comic
    0.43
     hydrology
    0.43
    Activations Density 0.000%

    No Known Activations