© 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. 70728
    Prev
    Next
    INDEX
    Explanations

    square root calculation

    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
    </b>
    -1.41
     momentan
    -1.13
     sadece
    -1.06
    </h5>
    -1.05
    shadowOpacity
    -1.02
    posedge
    -0.98
     hiç
    -0.98
     Kyoto
    -0.97
    ercice
    -0.97
     {},
    -0.96
    POSITIVE LOGITS
     ajan
    1.27
     other
    1.27
     optik
    1.23
     noin
    1.22
     frek
    1.20
     seksi
    1.20
     kony
    1.19
    ֺ
    1.18
     abiye
    1.16
     kov
    1.16
    Activations Density 0.024%

    No Known Activations