© 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. 102499
    Prev
    Next
    INDEX
    Explanations

    making inferences

    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
    .*")]
    -2.64
    篥
    -2.41
    
    -2.20
    
    -2.19
     het
    -2.19
     hermosos
    -2.16
    </h1>
    -2.13
    ઁ
    -2.09
     joyas
    -2.09
     одной
    -2.09
    POSITIVE LOGITS
     and
    2.14
     
    2.03
    ,
    2.02
     weiße
    1.95
    </em>
    1.94
     blaue
    1.94
     kwamba
    1.90
     übri
    1.84
     verbess
    1.80
     komplette
    1.80
    Activations Density 0.006%

    No Known Activations