© 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. 15496
    Prev
    Next
    INDEX
    Explanations

    get the: your, their, 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
     şirket
    -1.35
    給
    -1.31
     promoción
    -1.30
    趼
    -1.29
    skrä
    -1.27
     bordado
    -1.27
     aktivitet
    -1.27
    给
    -1.25
     trám
    -1.24
     gorro
    -1.23
    POSITIVE LOGITS
     rid
    2.09
     into
    1.70
     glimpse
    1.32
     from
    1.23
     neuesten
    1.21
     glimpses
    1.18
     hold
    1.16
     Nowadays
    1.16
     results
    1.15
     started
    1.15
    Activations Density 0.051%

    No Known Activations