© 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. 110910
    Prev
    Next
    INDEX
    Explanations

    swan event, AC joint, bringing in, glossary with

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

    a specific phrase

    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
    r
    0.50
     Reasons
    0.47
     CER
    0.45
     TER
    0.45
    0.45
     Tro
    0.45
    کاری
    0.45
     Spre
    0.45
     VER
    0.44
     Vary
    0.44
    POSITIVE LOGITS
     районе
    0.52
     voisinage
    0.52
    ጒ
    0.52
     embod
    0.50
    იღ
    0.49
    ጕ
    0.49
     сентября
    0.49
     needful
    0.49
    ዪ
    0.49
     गाड़ी
    0.48
    Activations Density 0.000%

    No Known Activations