© 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. 241407
    Prev
    Next
    INDEX
    Explanations

    London, Lancashire, Gem, education

    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
    തി
    0.57
    സി
    0.53
    اويه
    0.50
     coração
    0.50
    র্দ
    0.49
    ཱ
    0.49
     interesa
    0.49
    ೂರ್ವ
    0.48
    クリスマス
    0.47
    টিয়া
    0.47
    POSITIVE LOGITS
     iPads
    0.45
     Industrial
    0.45
    ​
    0.44
     Inventor
    0.44
     ​
    0.43
     iPad
    0.43
     Motley
    0.42
     Python
    0.42
     KID
    0.41
     Do
    0.41
    Activations Density 0.001%

    No Known Activations