© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41419
    Prev
    Next
    INDEX
    Explanations

    God, Allah, divine titles

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

    world, palace, or foreign words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nooit
    0.42
     Dentistry
    0.41
     cannot
    0.40
     restrictive
    0.40
     seves
    0.40
     Dental
    0.40
     ل
    0.40
     สามารถ
    0.40
     Strictly
    0.40
     restricts
    0.40
    POSITIVE LOGITS
    äjä
    0.44
    ಬಹು
    0.42
    明らか
    0.41
    想定
    0.40
     अमीर
    0.39
     सहानु
    0.39
    НЫ
    0.39
    垓
    0.39
     erwart
    0.38
    乐观
    0.38
    Activations Density 0.000%

    No Known Activations