© 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. 153833
    Prev
    Next
    INDEX
    Explanations

    Arab Republic

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

    initial attraction

    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
     an
    0.51
     alanı
    0.49
     oure
    0.48
     Waterloo
    0.46
     unm
    0.46
     м
    0.46
     meny
    0.46
     watery
    0.46
     m
    0.45
     damp
    0.45
    POSITIVE LOGITS
    zam
    0.50
    gew
    0.46
    glut
    0.46
    enzie
    0.46
    istles
    0.46
     التأ
    0.46
    zám
    0.46
    glucos
    0.46
    ्वेस्ट
    0.45
     Pupils
    0.45
    Activations Density 0.000%

    No Known Activations