© 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. 212632
    Prev
    Next
    INDEX
    Explanations

    CAR activities

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

    more than

    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
     Очень
    0.53
     Coatings
    0.53
     Verenigde
    0.52
    )\|_{\
    0.50
    ອີ
    0.48
    ottest
    0.47
     ದೊ
    0.47
     Согласно
    0.47
    Np
    0.46
    垁
    0.46
    POSITIVE LOGITS
    naked
    0.42
    deviation
    0.41
    nah
    0.41
    degrees
    0.40
     canonical
    0.40
    dess
    0.39
     عبارت
    0.39
     propuesta
    0.38
     retten
    0.38
     excess
    0.38
    Activations Density 0.001%

    No Known Activations