© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25546
    Prev
    Next
    INDEX
    Explanations

    Angel of

    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
    ּוֹ
    -1.70
    ֶּ
    -1.55
    ַּ
    -1.32
     September
    -1.23
    ִּ
    -1.20
     silnika
    -1.13
     it
    -1.11
     November
    -1.10
    ıyoruz
    -1.09
    ₙ
    -1.09
    POSITIVE LOGITS
     specif
    1.24
     augmenter
    1.23
    generic
    1.22
     يبدو
    1.21
    ῷ
    1.21
     effectuer
    1.20
    ︐
    1.18
     گیاه
    1.15
    Avec
    1.15
     devast
    1.15
    Activations Density 0.009%

    No Known Activations