© 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. 15565
    Prev
    Next
    INDEX
    Explanations

    use of a

    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
     zelve
    -1.33
    流畅
    -1.23
    ými
    -1.21
     gemeenten
    -1.18
     geïsole
    -1.15
     why
    -1.14
     zacht
    -1.12
     voordelen
    -1.10
    corrhi
    -1.09
     voldoende
    -1.09
    POSITIVE LOGITS
     a
    2.63
     an
    1.71
     to
    1.63
     the
    1.38
    "
    1.27
     another
    1.18
    زيل
    1.17
     conceito
    1.16
     (
    1.15
     salário
    1.09
    Activations Density 0.080%

    No Known Activations