© 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. 183614
    Prev
    Next
    INDEX
    Explanations

    yet to

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

    grammar and data structure

    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
    ![](
    0.47
    FolderName
    0.47
    各国
    0.43
     दरों
    0.42
    すご
    0.42
     Starting
    0.42
    记
    0.42
    িং
    0.41
     Trailer
    0.41
    ('../
    0.40
    POSITIVE LOGITS
    恝
    0.49
    ustus
    0.49
    alakip
    0.49
    uesto
    0.48
    asida
    0.48
    athyroid
    0.47
     Caste
    0.47
    odot
    0.46
    aceut
    0.46
    ᱘
    0.46
    Activations Density 0.001%

    No Known Activations