© 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. 86750
    Prev
    Next
    INDEX
    Explanations

    describing actions or systems

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

    system as

    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
    गुप्त
    0.45
     Абра
    0.45
    娌
    0.44
    ToPlot
    0.43
    ForRule
    0.43
    秩序
    0.43
    нець
    0.42
     порядок
    0.42
     процент
    0.42
     Horticultural
    0.42
    POSITIVE LOGITS
    Session
    0.58
    E
    0.51
    W
    0.49
    K
    0.49
     vuelve
    0.48
    B
    0.48
    was
    0.47
    stra
    0.47
    (
    0.46
    Ga
    0.46
    Activations Density 0.001%

    No Known Activations