© 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. 84061
    Prev
    Next
    INDEX
    Explanations

    claim preclusion

    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
    dreamstime
    -1.27
     Fotografía
    -1.21
     intending
    -1.18
     grupy
    -1.16
    (()=>
    -1.15
     totalSupply
    -1.15
     duomen
    -1.13
     allerede
    -1.13
    又能
    -1.08
     continue
    -1.06
    POSITIVE LOGITS
    Vegeu
    1.17
     таких
    1.11
     такие
    1.09
    roxene
    1.06
    ّل
    1.05
    搁
    1.05
    紲
    1.03
    Fallout
    1.02
    Ft
    1.01
    Ótimo
    1.01
    Activations Density 0.538%

    No Known Activations