© 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. 238091
    Prev
    Next
    INDEX
    Explanations

    home owners

    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
     تنها
    0.54
    tanh
    0.48
    â
    0.46
     shortlist
    0.46
    l
    0.45
    ilir
    0.45
    iris
    0.45
    t
    0.45
    ill
    0.44
    ANGE
    0.44
    POSITIVE LOGITS
    드를
    0.57
    감을
    0.49
    боре
    0.48
    땜
    0.47
    бок
    0.47
    фото
    0.47
     warten
    0.47
     onto
    0.46
    연구
    0.46
    感觉到
    0.45
    Activations Density 0.000%

    No Known Activations