© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75710
    Prev
    Next
    INDEX
    Explanations

    religious content and different languages

    np_acts-logits-general · gemini-2.5-flash-lite

    litres, times, parad, Respublik

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    atever
    0.39
    চল
    0.39
     catég
    0.39
    anking
    0.38
    ස්ට
    0.38
     tots
    0.38
     antennes
    0.38
     Woodstock
    0.38
    alley
    0.38
    Y
    0.38
    POSITIVE LOGITS
     ವೇ
    0.44
     תח
    0.42
     পুনরায়
    0.42
     వారు
    0.41
     disen
    0.41
    }$:
    0.40
     σε
    0.40
    äv
    0.40
     ตั้ง
    0.40
     તેઓ
    0.39
    Activations Density 0.002%

    No Known Activations