© 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. 196929
    Prev
    Next
    INDEX
    Explanations

    daughter, child, plenty, realistic

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

    explaining concepts like speed, basic, antiquated

    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
    owało
    0.51
    eningkatan
    0.51
     mettant
    0.49
    Cela
    0.48
    洴
    0.47
    ernen
    0.46
    ermanfaat
    0.46
    imak
    0.46
    牷
    0.46
    obal
    0.46
    POSITIVE LOGITS
     three
    0.52
     drauf
    0.49
     d
    0.49
     spring
    0.48
     daughter
    0.48
     four
    0.48
    চূ
    0.47
     Russian
    0.47
     socket
    0.46
     pod
    0.46
    Activations Density 0.001%

    No Known Activations