© 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. 84436
    Prev
    Next
    INDEX
    Explanations

    residential, insurance, part, algorithms, reinstated, opens

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

    language identification

    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
    想
    0.53
    ూ
    0.50
    زيد
    0.49
    易
    0.47
    网
    0.46
    ט
    0.46
    o
    0.45
    م
    0.44
     vo
    0.44
    《
    0.43
    POSITIVE LOGITS
     હતું
    0.52
     จำนวน
    0.51
    ulla
    0.50
    จำนวน
    0.50
     striées
    0.50
    ामध्ये
    0.50
     സംഭ
    0.50
    entino
    0.50
     început
    0.49
    ³/
    0.48
    Activations Density 0.000%

    No Known Activations