© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127690
    Prev
    Next
    INDEX
    Explanations

    occurring in various contexts

    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
    Negative Logits
    '
    -1.32
     australis
    -1.24
     they
    -1.22
    w
    -1.19
     had
    -1.15
    ve
    -1.14
    man
    -1.08
    ’
    -1.01
    s
    -1.01
     The
    -0.99
    POSITIVE LOGITS
     jednej
    1.20
     occurring
    1.19
     aspetto
    1.16
    ciech
    1.15
     vistazo
    1.13
     klasa
    1.12
    вање
    1.11
     artikelen
    1.11
     voordelen
    1.11
    小さ
    1.09
    Activations Density 0.203%

    No Known Activations