© 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. 187729
    Prev
    Next
    INDEX
    Explanations

    geographic and linguistic diversity

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

    filters and delivery types

    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
     Get
    0.53
     Large
    0.52
     Walking
    0.51
     t
    0.51
     Ninja
    0.51
     That
    0.49
     sumo
    0.49
     some
    0.49
     Nuk
    0.49
     g
    0.49
    POSITIVE LOGITS
    ológicos
    0.49
     соответствующих
    0.48
    🖌
    0.47
    ոն
    0.47
     jurídica
    0.46
    нда
    0.46
    췌
    0.46
    ència
    0.46
     vadati
    0.46
    属
    0.45
    Activations Density 0.001%

    No Known Activations