© 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. 59619
    Prev
    Next
    INDEX
    Explanations

    Paraguay

    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
    轳
    -2.38
     This
    -2.28
    }
    -2.25
    旆
    -2.23
     amounting
    -2.08
     начинают
    -2.08
    了她
    -2.03
    乆
    -2.02
    惲
    -1.98
     haven
    -1.98
    POSITIVE LOGITS
    the
    3.05
    t
    2.78
     “
    2.67
    笵
    2.67
    <bos>
    2.34
    涐
    2.30
      
    2.19
    ᷆
    2.08
    喜歡
    2.06
    ↵
    2.02
    Activations Density 0.001%

    No Known Activations