© 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. 45904
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    errors and multilingual assertions

    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
    镶
    0.48
    Controls
    0.48
    TextInput
    0.47
     Graft
    0.45
    seg
    0.44
    ಾರದ
    0.44
    שורים
    0.44
    Edges
    0.44
    鑲
    0.44
    Own
    0.43
    POSITIVE LOGITS
     permiten
    0.47
     yılında
    0.46
     délé
    0.45
     nabíd
    0.45
    eku
    0.44
     permitirá
    0.44
     reclam
    0.43
     वॉ
    0.43
     રા
    0.42
     rằng
    0.42
    Activations Density 0.000%

    No Known Activations