© 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. 247180
    Prev
    Next
    INDEX
    Explanations

    local graphics and county names

    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
     thisobject
    0.49
     chuẩn
    0.48
    кт
    0.46
     влас
    0.45
    OBJECT
    0.45
    🇶
    0.45
     ಪ್ರಮಾಣ
    0.44
     объект
    0.44
     поведения
    0.44
    𐰞
    0.43
    POSITIVE LOGITS
     Moulin
    0.58
     Dresden
    0.55
     Damascus
    0.54
     Leuven
    0.54
     \
    0.51
     Mosley
    0.51
    큰
    0.51
     Augsburg
    0.50
     Bz
    0.49
     lou
    0.49
    Activations Density 0.000%

    No Known Activations