© 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. 22-GEMMASCOPE-RES-131K
    7. 25671
    Prev
    Next
    INDEX
    Explanations

    calls to action

    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_22/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
    썼
    -1.02
    ំ
    -0.97
    ٬
    -0.94
    Lett
    -0.92
     Städten
    -0.91
     turisti
    -0.90
     harap
    -0.90
     imobili
    -0.89
     Però
    -0.89
     testamento
    -0.88
    POSITIVE LOGITS
     őket
    1.20
    ↵↵↵
    1.09
     memutus
    1.08
     сейчас
    1.04
     now
    1.02
    ↵↵↵↵↵
    1.00
     from
    0.99
    晌
    0.98
    ↵↵↵↵
    0.96
     habló
    0.96
    Activations Density 0.030%

    No Known Activations