© 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. 6284
    Prev
    Next
    INDEX
    Explanations

    can access information

    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
    чём
    0.57
    nm
    0.55
    根
    0.50
    储备
    0.49
    6
    0.48
    ("\
    0.48
    مة
    0.48
    澈
    0.48
    9
    0.47
     மிகுந்த
    0.47
    POSITIVE LOGITS
     reproducing
    0.49
     zej
    0.45
    ངས་
    0.45
     فی
    0.45
     refinance
    0.45
     copywriting
    0.45
     automation
    0.45
     robotic
    0.44
     saluran
    0.44
     perjanjian
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.