© 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. 124188
    Prev
    Next
    INDEX
    Explanations

    accents and server setup

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

    image generation models and feature extractors

    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
    0.52
    fromi
    0.48
    нется
    0.48
     coarsely
    0.47
    сили
    0.47
     fusing
    0.46
    creatic
    0.46
    冑
    0.46
    陥
    0.46
    manı
    0.45
    POSITIVE LOGITS
    uffin
    0.45
    אס
    0.44
    ্যান্ড
    0.44
    gey
    0.43
     Schnell
    0.42
     Reglamento
    0.42
     voller
    0.42
     sezon
    0.41
     schnelle
    0.41
    ifle
    0.41
    Activations Density 0.000%

    No Known Activations