© 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. 73489
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     &
    -1.23
    -1.14
    </strong>
    -1.13
     THE
    -1.09
    ărilor
    -1.04
     ndani
    -1.02
     isn
    -0.99
    :{

    -0.99
     kasama
    -0.98
     certains
    -0.97
    POSITIVE LOGITS
    Gön
    1.16
    んじゃ
    1.13
     NIGER
    1.05
    takings
    1.04
     ACCIDENT
    1.02
     váy
    1.00
    這裡
    1.00
     héri
    1.00
     jogar
    0.99
    なー
    0.99
    Activations Density 0.001%
    No Known Activations