© 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. 160836
    Prev
    Next
    INDEX
    Explanations

    training 101

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

    scenarios and descriptions

    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
     设备
    0.52
     單
    0.51
     وبر
    0.51
     البد
    0.50
     ويل
    0.48
     على
    0.46
     الاسلام
    0.46
     وير
    0.46
    া
    0.46
     作为
    0.46
    POSITIVE LOGITS
     ei
    0.49
     boiled
    0.49
     vertically
    0.47
     merged
    0.47
     Tuesday
    0.46
     difficulty
    0.45
     zipped
    0.45
     depan
    0.44
     bruising
    0.44
     nutty
    0.44
    Activations Density 0.000%

    No Known Activations