© 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. 122495
    Prev
    Next
    INDEX
    Explanations

    around the second quarter

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

    predicting answer format

    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
     besk
    0.47
    ването
    0.47
     август
    0.47
     getir
    0.46
    jaty
    0.46
    ร
    0.45
     pued
    0.45
    द
    0.45
    Nan
    0.44
    邕
    0.44
    POSITIVE LOGITS
     angiogenic
    0.52
     encompassed
    0.50
     accusantium
    0.49
    ક્ટર
    0.49
     peaking
    0.48
     বো
    0.46
     volumetric
    0.46
     theologians
    0.46
     articular
    0.46
    ങ്ങളുടെ
    0.46
    Activations Density 0.003%

    No Known Activations