© 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. 224228
    Prev
    Next
    INDEX
    Explanations

    your computer, is true

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

    recognizing immediately two

    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
     «
    0.50
     yě
    0.48
     више
    0.43
     همچنین
    0.42
     हे
    0.42
     со
    0.42
     Alpes
    0.41
    特色的
    0.41
    nya
    0.41
    たっぷり
    0.41
    POSITIVE LOGITS
    둴
    0.47
    causing
    0.47
    answered
    0.47
    ख्ती
    0.47
    neurons
    0.45
    recorded
    0.44
    amélioration
    0.44
    뷸
    0.44
    ᆹ
    0.44
    었고
    0.44
    Activations Density 0.000%

    No Known Activations