© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76663
    Prev
    Next
    INDEX
    Explanations

    link there

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

    specific questions for clarification

    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
     वॉल
    0.54
     божомолу
    0.52
     აღმასრულებელი
    0.50
     செயற்ப
    0.49
     نموذج
    0.48
     പ്രവര്‍ത്തന
    0.47
    }$;
    0.46
     இயக்க
    0.46
     활
    0.45
    𒄭
    0.45
    POSITIVE LOGITS
     
    0.56
    .
    0.56
    %
    0.52
    Т
    0.51
     these
    0.49
    ন
    0.48
     this
    0.46
    四
    0.46
    کا
    0.46
    *
    0.46
    Activations Density 0.000%

    No Known Activations