© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14849
    Prev
    Next
    INDEX
    Explanations

    New York, Buffalo, Bills

    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
     a
    -1.48
    fileID
    -1.07
    B
    -1.05
    </h3>
    -1.01
     \
    -1.00
    }
    -0.99
     Their
    -0.98
    _
    -0.97
    Australia
    -0.97
    </em>
    -0.97
    POSITIVE LOGITS
     SUNY
    1.28
    нні
    1.26
    しちゃ
    1.23
    塤
    1.16
     Mohawk
    1.16
    asiswa
    1.16
    睨
    1.13
    講座
    1.13
    dáms
    1.11
    lequin
    1.11
    Activations Density 0.070%

    No Known Activations