© 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. 130893
    Prev
    Next
    INDEX
    Explanations

    than you

    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
     dago
    -1.35
    そういえば
    -1.30
    拍了拍
    -1.27
    ¹)
    -1.26
    ôs
    -1.26
    )　
    -1.22
    dreaming
    -1.22
     Dopo
    -1.22
     empat
    -1.22
     lucu
    -1.22
    POSITIVE LOGITS
     it
    1.91
    </h2>
    1.55
     your
    1.38
     its
    1.37
     you
    1.26
    着脸
    1.23
    $}
    1.23
     also
    1.20
     kém
    1.19
     նաև
    1.19
    Activations Density 0.214%

    No Known Activations