© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19483
    Prev
    Next
    INDEX
    Explanations

    where I stand

    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
     радика
    0.44
     BUILDING
    0.42
    )\|_{\
    0.42
     máxim
    0.41
    ʚ
    0.41
    akkhand
    0.40
     radically
    0.40
     thisStudent
    0.40
     ~(
    0.39
     radicals
    0.39
    POSITIVE LOGITS
     कारण
    0.47
    ed
    0.46
     Wave
    0.46
     sender
    0.46
     Doesn
    0.46
     Strain
    0.45
     Remains
    0.45
     rangkaian
    0.45
     Conexion
    0.45
    यिक
    0.45
    Activations Density 0.009%

    No Known Activations