© 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. 151530
    Prev
    Next
    INDEX
    Explanations

    Samuel and Saul

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

    justifies larger, discriminatory line

    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
    ᓱ
    0.47
    க்கப்பட்ட
    0.45
    嫄
    0.45
    भावस्था
    0.44
    ínű
    0.43
    ellular
    0.42
     सिंग
    0.41
     ہمارے
    0.41
    ্যন্তরীণ
    0.41
    инг
    0.41
    POSITIVE LOGITS
     devoted
    0.52
     diners
    0.45
     diner
    0.44
    (
    0.44
    Y
    0.43
    oyo
    0.42
    ps
    0.42
    restaurant
    0.42
     који
    0.42
    sta
    0.41
    Activations Density 0.001%

    No Known Activations