© 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. 71330
    Prev
    Next
    INDEX
    Explanations

    months and numbers

    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
     my
    -1.55
     I
    -1.50
    ׇ
    -1.34
     چربی
    -1.20
     musées
    -1.20
     zanah
    -1.17
     ideas
    -1.16
     Pfar
    -1.16
     włosów
    -1.13
    %";
    -1.13
    POSITIVE LOGITS
    וּ
    1.66
    ּוֹ
    1.48
     Décembre
    1.42
     Septembre
    1.36
    וֹ
    1.33
     Février
    1.31
     Août
    1.30
     Octobre
    1.27
    ַּ
    1.25
     رژ
    1.25
    Activations Density 0.212%

    No Known Activations