© 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. 257485
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    s
    0.51
    2
    0.50
    ukary
    0.48
     mortar
    0.48
    .
    0.48
    شة
    0.47
     друг
    0.46
    4
    0.45
    Ratio
    0.44
    ().
    0.43
    POSITIVE LOGITS
    lüğ
    0.58
    ্টি
    0.55
     İyi
    0.50
    ۪
    0.49
     กราบ
    0.48
    хів
    0.47
    ದ್ದರಿಂದ
    0.47
     Idha
    0.47
     정치
    0.46
    𝗧
    0.46
    Activations Density 0.000%

    No Known Activations