© 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. 201229
    Prev
    Next
    INDEX
    Explanations

    films, skills, parents, dating

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

    drawing shapes

    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
    níci
    0.52
     komun
    0.51
     کوم
    0.47
    ものは
    0.46
     objekt
    0.45
    되지
    0.45
    nými
    0.45
    -
    0.45
    ことができる
    0.44
    ckte
    0.44
    POSITIVE LOGITS
    lineEdit
    0.49
    <<<<
    0.48
    ઉસ
    0.47
     saque
    0.47
    痉
    0.45
     Capcom
    0.44
    ueba
    0.44
     ২০১৬
    0.43
     సూపర్
    0.43
     fireman
    0.42
    Activations Density 0.001%

    No Known Activations