© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56617
    Prev
    Next
    INDEX
    Explanations

    same vein, similar feel, with numbers, Power BI, dogs mating

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    zahlen
    0.46
    üs
    0.46
     पाया
    0.44
    ंतर
    0.43
    レーション
    0.43
    scopic
    0.41
     गया
    0.40
     प्राय
    0.40
    captcha
    0.40
    1
    0.40
    POSITIVE LOGITS
     postice
    0.48
     professional
    0.44
    调节
    0.43
     profesional
    0.42
     профессиона
    0.42
    收取
    0.42
     tuna
    0.42
     professionnelle
    0.41
     docked
    0.41
     pomaga
    0.41
    Activations Density 0.008%

    No Known Activations