© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213859
    Prev
    Next
    INDEX
    Explanations

    AM radio, FM radio, DAB radio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cloning
    0.42
     클
    0.42
     кли
    0.41
    ն
    0.41
     cloning
    0.39
     Ген
    0.39
     swallow
    0.38
    導入
    0.38
     земля
    0.38
     ク
    0.37
    POSITIVE LOGITS
    ជ្
    0.42
     empêcher
    0.39
    ással
    0.38
    =")"
    0.38
     Vara
    0.37
     Myth
    0.36
    ্যাস
    0.36
     Vera
    0.36
     Myc
    0.36
    yd
    0.36
    Activations Density 0.005%

    No Known Activations