© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68778
    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
     its
    -1.10
     these
    -1.09
     Anwendungs
    -1.06
     different
    -1.05
     cinturón
    -1.02
     kvinna
    -0.99
    }*/
    -0.98
     besök
    -0.97
    ('../../../
    -0.97
    کیف
    -0.96
    POSITIVE LOGITS
    があり
    1.33
     nostri
    1.16
    Anno
    1.13
    arked
    1.04
     NEV
    1.03
     achie
    1.02
    があります
    1.01
     ORO
    1.00
    В
    0.99
    がありますが
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.