© 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. 244209
    Prev
    Next
    INDEX
    Explanations

    clinical Telekom explaining

    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
     nanotubes
    0.49
    cD
    0.48
    cC
    0.48
    testX
    0.48
    rH
    0.47
    {}'.
    0.46
    xg
    0.46
    කි
    0.45
     lặng
    0.45
    চ্য
    0.45
    POSITIVE LOGITS
    哳
    0.57
     Bonaparte
    0.49
     काजल
    0.49
     Citrus
    0.46
     सहारे
    0.45
     આમ
    0.44
     Borrow
    0.44
     Finishing
    0.44
     Teaching
    0.44
     Responsibility
    0.44
    Activations Density 0.000%

    No Known Activations