© 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. 159385
    Prev
    Next
    INDEX
    Explanations

    phrases often followed by a word

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

    lists, books, and articles

    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
     spitting
    0.50
     disagreements
    0.49
    z
    0.46
    u
    0.46
    ungkinkan
    0.44
     겁
    0.44
     당시
    0.44
     лоша
    0.44
     thirty
    0.43
    ivanja
    0.43
    POSITIVE LOGITS
    🥚
    0.55
    Iniciar
    0.53
    Primero
    0.51
    StartState
    0.50
    Одна
    0.49
    Ros
    0.49
    Extended
    0.49
    Estados
    0.48
    ('\
    0.48
    Ин
    0.48
    Activations Density 0.000%

    No Known Activations