© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163984
    Prev
    Next
    INDEX
    Explanations

    related words following specific words

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

    Direct Connect

    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
    in
    0.52
    heap
    0.47
     распоря
    0.47
    週
    0.47
    is
    0.47
    。
    0.46
     Foundations
    0.45
    躋
    0.45
    ö
    0.45
    ماً
    0.45
    POSITIVE LOGITS
     foragers
    0.52
     coaster
    0.51
    echolog
    0.49
     ماشینونو
    0.47
     reflector
    0.46
     withered
    0.46
    LastGen
    0.46
    ExternalTaskPojo
    0.46
     avenge
    0.45
     impresora
    0.44
    Activations Density 0.001%

    No Known Activations