© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125597
    Prev
    Next
    INDEX
    Explanations

    Inner Compass

    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
     반려
    0.46
    শালী
    0.45
     eso
    0.44
     বা
    0.41
     Garza
    0.41
     pesca
    0.41
     вами
    0.40
    舞
    0.40
     inflatable
    0.40
     canola
    0.40
    POSITIVE LOGITS
    ides
    0.46
    ير
    0.43
    뇌
    0.42
    Ü
    0.41
    Again
    0.41
     weer
    0.40
    يف
    0.40
    qvist
    0.40
     igjen
    0.40
    خ
    0.39
    Activations Density 0.005%

    No Known Activations