© 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. 134724
    Prev
    Next
    INDEX
    Explanations

    inquiring about information

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

    automation and operations

    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
    ిక
    0.57
     серии
    0.49
     Север
    0.48
    முடி
    0.47
    燚
    0.47
     participated
    0.46
     Вулкан
    0.46
     ponder
    0.45
    трибу
    0.45
    ^*$
    0.45
    POSITIVE LOGITS
    RIGHT
    0.52
    THAT
    0.48
    ا
    0.48
    FOUR
    0.46
    decreasing
    0.46
    餓
    0.45
    REQUEST
    0.44
    reducing
    0.44
     removing
    0.43
    POLICY
    0.43
    Activations Density 0.001%

    No Known Activations