© 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. 39736
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    -2.14
     wirklich
    -1.52
    .
    -1.48
     limitaciones
    -1.48
    ’
    -1.41
     portions
    -1.39
     terület
    -1.35
    值的
    -1.34
     restricciones
    -1.33
     kinds
    -1.32
    POSITIVE LOGITS
     that
    3.31
     of
    1.91
    <bos>
    1.60
     granja
    1.58
     whose
    1.48
     που
    1.47
     Svizzera
    1.45
     for
    1.41
     keduanya
    1.41
     suhu
    1.41
    Activations Density 0.912%

    No Known Activations