© 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. 10-GEMMASCOPE-RES-131K
    7. 43950
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
    точник
    -1.34
     zarówno
    -1.32
     both
    -1.28
    -1.27
     many
    -1.27
     wielu
    -1.24
    anglicky
    -1.23
    EI
    -1.23
    ↵
    -1.22
    ingeki
    -1.18
    POSITIVE LOGITS
     باشد
    1.34
     also
    1.29
     first
    1.27
     detta
    1.27
    蔔
    1.25
     meno
    1.23
    上の
    1.20
    Another
    1.18
     this
    1.18
     metaphorical
    1.14
    Activations Density 0.044%
    No Known Activations