© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 164936
    Prev
    Next
    INDEX
    Explanations

    automated detection

    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
     finite
    0.40
    <unused17>
    0.39
     दबाव
    0.37
    Ethiop
    0.37
     有限
    0.36
    <unused7>
    0.36
    իր
    0.36
    課題
    0.36
     presión
    0.35
    Sicilian
    0.35
    POSITIVE LOGITS
     formats
    0.37
    itures
    0.37
    etlen
    0.37
    ậ
    0.37
    ঙ্খ
    0.36
     being
    0.35
     k
    0.35
    roh
    0.35
    k
    0.34
     excl
    0.34
    Activations Density 0.000%

    No Known Activations