© 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. 141855
    Prev
    Next
    INDEX
    Explanations

    completion items or phrases

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

    offer solace or shit

    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
    О
    0.51
    И
    0.50
    अग
    0.49
     médias
    0.49
    Quel
    0.48
    电器
    0.48
    இ
    0.48
    그
    0.47
    ୈ
    0.46
    Від
    0.46
    POSITIVE LOGITS
     Wali
    0.50
     থে
    0.50
     scanty
    0.48
     consect
    0.47
    irittura
    0.46
     Ababa
    0.46
    rados
    0.46
    .。
    0.45
     বাঁচাতে
    0.45
    だけでなく
    0.43
    Activations Density 0.000%

    No Known Activations