© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136367
    Prev
    Next
    INDEX
    Explanations

    numerical quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     familien
    0.44
    /
    0.43
    ને
    0.42
     similares
    0.39
    ':
    0.38
    adays
    0.38
     sighted
    0.38
     библиотеки
    0.38
     coher
    0.37
     Nasional
    0.37
    POSITIVE LOGITS
     trzech
    0.45
     three
    0.44
     drei
    0.42
     үш
    0.41
     four
    0.41
     trois
    0.41
     যেকোনো
    0.40
     थ्री
    0.40
    ➊
    0.40
     Two
    0.40
    Activations Density 0.005%

    No Known Activations