© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72697
    Prev
    Next
    INDEX
    Explanations

    asking for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ông
    -1.88
     guerrero
    -1.83
    芣
    -1.72
    
    -1.60
     både
    -1.58
     cerdo
    -1.58
     ماذا
    -1.55
     exemplaires
    -1.55
    鉿
    -1.55
    Türk
    -1.55
    POSITIVE LOGITS
     to
    2.58
     about
    2.19
    .
    1.91
     It
    1.64
    de
    1.63
     desired
    1.57
     because
    1.51
     due
    1.48
     This
    1.41
     that
    1.36
    Activations Density 0.020%

    No Known Activations