© 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. 177914
    Prev
    Next
    INDEX
    Explanations

    honour graduates

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

    explaining with examples

    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
     desirable
    0.43
    ā
    0.42
     disorder
    0.41
     Reno
    0.41
     Defects
    0.41
    ดย
    0.40
     Disorder
    0.40
     ঘটেছে
    0.40
    <0x83>
    0.39
     survival
    0.39
    POSITIVE LOGITS
     unequiv
    0.53
     空気
    0.48
     penampilan
    0.46
    Neighbors
    0.45
     njihov
    0.45
    onActivityResult
    0.44
    甜蜜
    0.44
     remporté
    0.44
    Kost
    0.44
     garantir
    0.43
    Activations Density 0.000%

    No Known Activations