© 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. 127259
    Prev
    Next
    INDEX
    Explanations

    updated dates and recipes

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

    evolution and individuals

    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
    군의
    0.45
    활
    0.45
    嗕
    0.45
    ⓡ,
    0.44
    оз
    0.43
    ér
    0.42
    embl
    0.41
    鲨
    0.41
    ®.
    0.41
    án
    0.40
    POSITIVE LOGITS
     Еўро
    0.49
     trest
    0.44
     Rydberg
    0.44
    w
    0.44
    \]
    0.43
    swire
    0.42
     ძალიან
    0.42
     Fairmont
    0.42
     Neste
    0.41
    ToAdd
    0.41
    Activations Density 0.001%

    No Known Activations