© 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. 26240
    Prev
    Next
    INDEX
    Explanations

    wildcard character `*`

    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
     this
    -1.12
     forro
    -1.04
     évé
    -1.00
     harapan
    -0.98
     microfibra
    -0.98
     Spanyol
    -0.98
    ﹕
    -0.96
     Belgique
    -0.92
     lavadora
    -0.91
     %).
    -0.90
    POSITIVE LOGITS
    所以在
    1.06
    ഞ
    1.06
    các
    1.02
    matitis
    0.99
     egentligen
    0.98
     gelegt
    0.97
     begrenzt
    0.96
     Performs
    0.91
     afore
    0.91
     március
    0.89
    Activations Density 0.001%

    No Known Activations