© 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. 209543
    Prev
    Next
    INDEX
    Explanations

    before vehicles, after, calculated

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

    file types, api codes, price points

    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
     Когда
    0.53
    Mechanical
    0.47
     помогают
    0.47
     Når
    0.45
    Managers
    0.45
    ود
    0.44
    观
    0.44
     getServer
    0.43
     ஆனால்
    0.42
     Mechanical
    0.42
    POSITIVE LOGITS
     uncle
    0.48
    !");
    0.47
     ACHIE
    0.47
     empresario
    0.46
     midway
    0.46
     millions
    0.44
     halfway
    0.44
     IMM
    0.44
    !!”
    0.44
     estimator
    0.43
    Activations Density 0.000%

    No Known Activations