© 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. 21097
    Prev
    Next
    INDEX
    Explanations

    multilingual phrases and names

    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
      
    -2.41
    derdag
    -2.22
     insgesamt
    -2.20
    臜
    -2.19
            
    -2.16
     ofreci
    -2.13
     سایر
    -2.09
     dijeron
    -2.08
     of
    -2.06
    蠖
    -2.00
    POSITIVE LOGITS
    It
    2.80
    蹓
    2.67
    綃
    2.56
    The
    2.41
     対策
    2.36
     帶
    2.31
    數字
    2.31
    熒
    2.27
     壓
    2.27
     "'";
    2.27
    Activations Density 0.004%

    No Known Activations