© 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. 154101
    Prev
    Next
    INDEX
    Explanations

    existing conditions, response had, faith centre

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

    history and development

    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
    istler
    0.54
    붉
    0.51
    Сан
    0.48
    Всем
    0.47
    Otra
    0.47
    ñas
    0.47
    sld
    0.46
    été
    0.46
    浠
    0.46
    waitSeconds
    0.45
    POSITIVE LOGITS
     chromium
    0.57
     pregnancy
    0.54
     tyrosine
    0.53
     un
    0.52
     di
    0.52
     pandas
    0.50
     tubercul
    0.50
     d
    0.50
     dua
    0.49
     pregn
    0.49
    Activations Density 0.000%

    No Known Activations