© 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. 239342
    Prev
    Next
    INDEX
    Explanations

    salt flats

    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
    𝘇
    0.46
     reactors
    0.45
    মের
    0.45
     that
    0.44
    ্ব
    0.43
    OR
    0.43
    ಿ
    0.43
     marketplaces
    0.42
    Penn
    0.41
    з
    0.41
    POSITIVE LOGITS
    嶙
    0.51
     TDC
    0.49
    dSample
    0.49
     abgest
    0.48
     Bc
    0.48
    鿁
    0.47
    淦
    0.47
     CDI
    0.47
     tapp
    0.46
     ကု
    0.46
    Activations Density 0.001%

    No Known Activations