© 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. 99489
    Prev
    Next
    INDEX
    Explanations

    programming data types and structures

    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
    asında
    -1.41
    для
    -1.31
    XmlSchema
    -1.24
    })$.
    -1.23
     Keine
    -1.19
    ERS
    -1.18
    ulence
    -1.17
    nitzel
    -1.16
     möjligt
    -1.16
     Valid
    -1.14
    POSITIVE LOGITS
     that
    1.59
     also
    1.58
     it
    1.44
     otros
    1.41
     still
    1.35
     adquirido
    1.28
     outros
    1.26
     has
    1.23
     however
    1.23
     costru
    1.22
    Activations Density 0.131%

    No Known Activations