© 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. 26580
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    琊
    -1.10
     reveló
    -1.09
     incluye
    -1.02
    RAINE
    -1.02
    huur
    -1.01
    就此
    -1.01
    economia
    -0.98
    Étymologie
    -0.97
     wrze
    -0.96
     episódio
    -0.96
    POSITIVE LOGITS
     will
    1.56
     when
    1.14
    when
    1.00
     is
    1.00
    𝘢
    0.99
     nostru
    0.98
     like
    0.97
    ë
    0.95
     described
    0.94
     когда
    0.93
    Activations Density 0.000%

    No Known Activations