© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78914
    Prev
    Next
    INDEX
    Explanations

    reflection of information

    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_31_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
     URLs
    0.40
     strides
    0.40
     GPIO
    0.40
     résolution
    0.40
    ranks
    0.39
    adale
    0.39
    務
    0.39
     гід
    0.38
     प्रस
    0.38
     stirs
    0.38
    POSITIVE LOGITS
    یره
    0.57
     Auschwitz
    0.48
     opposites
    0.48
     आजाद
    0.47
     Pulitzer
    0.47
    О
    0.47
    ukur
    0.47
     позволит
    0.46
    Автор
    0.46
    ایه
    0.46
    Activations Density 0.002%

    No Known Activations