© 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. 26173
    Prev
    Next
    INDEX
    Explanations

    temporal expressions

    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
    ;
    -1.70
     my
    -1.52
     I
    -1.31
     a
    -1.30
     ads
    -1.28
     S
    -1.26
     D
    -1.25
     as
    -1.24
     and
    -1.23
     gdyż
    -1.23
    POSITIVE LOGITS
     there
    1.66
     bateria
    1.34
     ideen
    1.24
    ︕
    1.21
     joão
    1.20
     fournisseur
    1.19
     aussit
    1.19
     doña
    1.18
     แท
    1.16
     komik
    1.16
    Activations Density 0.050%

    No Known Activations