© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20928
    Prev
    Next
    INDEX
    Explanations

    device and related concepts

    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_10/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
     abiye
    -1.50
     tissus
    -1.35
     kollu
    -1.35
    igth
    -1.31
     dévelo
    -1.30
     tunik
    -1.29
    voir
    -1.27
     WENT
    -1.27
     sava
    -1.27
     desenli
    -1.26
    POSITIVE LOGITS
     but
    1.55
    uksessa
    1.51
     üblichen
    1.45
    </b>
    1.44
     también
    1.41
    quial
    1.41
    Ἡ
    1.39
    pric
    1.38
    =-\
    1.38
     ersten
    1.38
    Activations Density 0.033%

    No Known Activations