© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12693
    Prev
    Next
    INDEX
    Explanations

    movement followed by direction

    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
     kön
    -1.64
     parfüm
    -1.38
     fotográfico
    -1.31
     köp
    -1.29
    pecha
    -1.23
     läs
    -1.21
     gelas
    -1.20
     saisi
    -1.20
     régl
    -1.19
    ográ
    -1.18
    POSITIVE LOGITS
    </em>
    1.25
     to
    1.21
    A
    1.20
    ut
    1.17
     across
    1.14
     in
    1.11
     along
    1.10
    G
    1.08
    by
    1.07
     again
    1.06
    Activations Density 0.002%

    No Known Activations