© 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. 10-GEMMASCOPE-RES-131K
    7. 67152
    Prev
    Next
    INDEX
    Explanations

    for this purpose

    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_10/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
     новая
    -2.38
    鱟
    -2.23
     Voraussetzung
    -2.20
     koła
    -2.20
    calça
    -2.20
    顺便
    -2.19
    咴
    -2.14
    derdag
    -2.13
     then
    -2.11
    tischen
    -2.11
    POSITIVE LOGITS
    The
    2.66
    ſelves
    2.50
     них
    2.39
    “
    2.38
    1
    2.30
    as
    2.25
    توض
    2.20
     tredje
    2.19
     Around
    2.16
    ("
    2.14
    Activations Density 0.003%

    No Known Activations