© 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. 231572
    Prev
    Next
    INDEX
    Explanations

    heating installation

    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
    ຜະລິດຕະພັນ
    0.50
    عنی
    0.50
    ુ
    0.48
    یا
    0.47
     especiais
    0.47
     palmit
    0.46
    лянчук
    0.45
    irii
    0.45
    መሪያ
    0.45
    ファイ
    0.44
    POSITIVE LOGITS
    du
    0.49
     ক্রমা
    0.45
    gren
    0.43
    gra
    0.43
    3
    0.43
    fe
    0.42
    duino
    0.42
     သူမ
    0.42
    -
    0.42
    vær
    0.42
    Activations Density 0.002%

    No Known Activations