© 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. 71520
    Prev
    Next
    INDEX
    Explanations

    undisputed entry

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

    content and structure

    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
     ukon
    0.48
    iczne
    0.46
     ဗ
    0.43
    ěru
    0.42
     heterod
    0.42
     Iris
    0.42
     ovip
    0.42
     iris
    0.42
     bạn
    0.41
     Schottky
    0.41
    POSITIVE LOGITS
    堈
    0.49
    內容
    0.47
    อาหาร
    0.46
    भा
    0.45
    КА
    0.45
    <0xD4>
    0.45
    ोजन
    0.44
    MAE
    0.44
    Rn
    0.44
     रंजन
    0.44
    Activations Density 0.001%

    No Known Activations