© 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. 151794
    Prev
    Next
    INDEX
    Explanations

    words followed by specific words

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

    concepts and their contexts

    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
    互
    0.54
     وسائل
    0.53
    рано
    0.51
    阖
    0.49
    ровой
    0.49
    炉
    0.48
    愠
    0.48
    赓
    0.48
    扩散
    0.48
    nashvillehousing
    0.48
    POSITIVE LOGITS
    ?
    0.56
    a
    0.52
    3
    0.52
    ’
    0.52
     class
    0.51
     thirty
    0.51
     its
    0.50
     girl
    0.50
     would
    0.50
     three
    0.49
    Activations Density 0.000%

    No Known Activations