© 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. 120536
    Prev
    Next
    INDEX
    Explanations

    changing hierarchical structures

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

    prioritizing stability

    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
    ą
    0.53
    ır
    0.46
    &
    0.46
    at
    0.44
    lari
    0.44
    =
    0.44
    imately
    0.44
    \.
    0.44
    \
    0.44
    ės
    0.44
    POSITIVE LOGITS
     incênd
    0.47
    疑問
    0.46
     mannen
    0.45
     modus
    0.45
    ၽ
    0.44
     технику
    0.44
     coment
    0.44
     تشتغل
    0.44
    تب
    0.43
     wikipagina
    0.43
    Activations Density 0.000%

    No Known Activations