© 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. 44598
    Prev
    Next
    INDEX
    Explanations

    his family and dog

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

    recognizing common abbreviations

    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
    н
    0.47
    ن
    0.47
     equiv
    0.46
    IKA
    0.46
    न
    0.45
    setInterval
    0.45
    খানা
    0.44
     intellectually
    0.44
    ס
    0.44
    MPI
    0.42
    POSITIVE LOGITS
    anoate
    0.53
    uparavant
    0.49
     කිරීමට
    0.46
    teger
    0.46
    க்கொள்ள
    0.46
     азо
    0.46
     prendre
    0.45
    ță
    0.45
     নির্ধার
    0.44
    鹈
    0.44
    Activations Density 0.000%

    No Known Activations