© 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. 65596
    Prev
    Next
    INDEX
    Explanations

    mission and vision statements

    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
    cipais
    -1.25
     zugelassen
    -1.23
    ěstí
    -1.16
     teorías
    -1.14
     conversaciones
    -1.11
     tématu
    -1.10
     conclusiones
    -1.10
     Fällen
    -1.10
     conocido
    -1.09
    ﾒ
    -1.09
    POSITIVE LOGITS
     and
    1.53
     its
    1.30
     mission
    1.22
     évé
    1.21
    :
    1.20
     goals
    1.14
     evenement
    1.14
     schu
    1.13
     tev
    1.10
     hizmet
    1.09
    Activations Density 0.021%

    No Known Activations