© 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. 104354
    Prev
    Next
    INDEX
    Explanations

    names and numbers

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

    misclassify, really, dwindling, visual

    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
    клады
    0.45
    η
    0.44
    욥
    0.43
    са
    0.43
    ப்பட
    0.43
    печа
    0.42
    দল
    0.41
    NATIONAL
    0.41
    ಿದ
    0.40
    කාර
    0.40
    POSITIVE LOGITS
     hitbox
    0.50
     مخ
    0.44
     swing
    0.43
     기능을
    0.42
    脳
    0.42
     উপলব্ধি
    0.42
     ဟ
    0.41
    kje
    0.41
     życia
    0.40
     സ്ഥ
    0.40
    Activations Density 0.000%

    No Known Activations