© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140137
    Prev
    Next
    INDEX
    Explanations

    frames per second or hertz

    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_16_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
    ية
    0.65
    م
    0.65
     क्रिप्ट
    0.61
    is
    0.59
    ون
    0.59
    یشه
    0.58
     cleric
    0.58
    ির
    0.57
    یه
    0.57
     enkelt
    0.57
    POSITIVE LOGITS
    Flood
    0.52
    AT
    0.52
    >(
    0.49
    টারি
    0.49
    Truck
    0.49
    Stack
    0.47
    ?
    0.47
    中学校
    0.47
    Washington
    0.46
    Tucker
    0.46
    Activations Density 0.001%

    No Known Activations