© 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. 186177
    Prev
    Next
    INDEX
    Explanations

    areas. Mercedes. prices. luxurious. pushing. $

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

    explaining how things relate

    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
    írus
    0.52
    ન્દ
    0.52
     consecuencias
    0.51
    λό
    0.50
    釹
    0.49
     difusión
    0.48
    وْ
    0.48
    يس
    0.48
    على
    0.48
    糖尿
    0.47
    POSITIVE LOGITS
    ry
    0.55
    ta
    0.55
    thy
    0.52
    thi
    0.50
    rak
    0.50
    sey
    0.49
    uji
    0.49
    submit
    0.48
    sm
    0.48
    cia
    0.47
    Activations Density 0.000%

    No Known Activations