© 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. 34182
    Prev
    Next
    INDEX
    Explanations

    all important

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

    growing up, filter lies, first-party data

    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
     combatt
    0.54
     délai
    0.54
    AndUpdate
    0.51
    艦
    0.50
     Гинд
    0.49
     اسرائی
    0.49
     Неза
    0.49
    пециа
    0.48
    ধারী
    0.48
     това
    0.47
    POSITIVE LOGITS
    dist
    0.44
    spare
    0.44
    0
    0.44
    gå
    0.43
    ಾಗಿದೆ
    0.41
    enged
    0.41
     posibilidad
    0.41
     gå
    0.41
    op
    0.40
    non
    0.40
    Activations Density 0.000%

    No Known Activations