© 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. 99933
    Prev
    Next
    INDEX
    Explanations

    if there is

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

    conditional logic in code or propositions

    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
     gerektiğini
    0.61
    ۰
    0.49
    ություն
    0.47
     diferentes
    0.47
     столь
    0.47
     المختلفة
    0.46
    生命的
    0.46
    しまった
    0.46
     ще
    0.46
     métiers
    0.45
    POSITIVE LOGITS
     there
    0.63
     either
    0.57
    Either
    0.55
    它是
    0.55
    :&
    0.55
    soever
    0.52
     is
    0.51
    In
    0.51
    there
    0.51
    either
    0.49
    Activations Density 0.077%

    No Known Activations