© 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. 240993
    Prev
    Next
    INDEX
    Explanations

    our

    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
     Indicates
    0.41
     Specifies
    0.39
    🔯
    0.38
    引擎
    0.38
    SIBILITY
    0.37
     наоборот
    0.36
    タリア
    0.36
     Builds
    0.35
    "/
    0.35
    線性
    0.35
    POSITIVE LOGITS
     nuestra
    0.51
     naš
    0.50
     উৎপাদনের
    0.48
     наші
    0.47
     naszego
    0.47
     আমাদের
    0.46
     naszym
    0.46
     ہماری
    0.45
     unsere
    0.45
    我們的
    0.44
    Activations Density 0.028%

    No Known Activations