© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67235
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     långt
    -1.16
    <bos>
    -1.13
    si
    -1.05
     cualquier
    -1.05
     лишь
    -1.02
     will
    -1.00
     endast
    -0.99
    o
    -0.99
    po
    -0.98
    point
    -0.98
    POSITIVE LOGITS
     one
    1.29
    magazin
    1.24
     sué
    1.20
     casque
    1.17
    gió
    1.16
     actrice
    1.15
     veau
    1.14
    ₄
    1.13
    springen
    1.12
     siè
    1.10
    Activations Density 0.040%

    No Known Activations