© 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. 154043
    Prev
    Next
    INDEX
    Explanations

    Dolly Parton, Salvador Dali

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

    dolly's pub

    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
    carouselExample
    0.41
     udara
    0.39
     ordnance
    0.39
     Tige
    0.39
     clicar
    0.39
     dicas
    0.38
     gec
    0.38
    瑕
    0.38
     redor
    0.37
    devices
    0.37
    POSITIVE LOGITS
    ɫ
    0.46
     অবস
    0.41
    blockSize
    0.40
    вшей
    0.39
    牆
    0.39
     மூட
    0.39
    कुंठ
    0.39
    ptime
    0.38
     Priorities
    0.38
     थिएटर
    0.38
    Activations Density 0.002%

    No Known Activations