© 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. 100442
    Prev
    Next
    INDEX
    Explanations

    space agencies and NASA

    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
    '
    -1.84
    блок
    -1.72
    虓
    -1.52
     trastornos
    -1.40
     paragraphe
    -1.35
    鄒
    -1.35
     polecam
    -1.30
    👺
    -1.30
     usize
    -1.29
    ▾
    -1.27
    POSITIVE LOGITS
     to
    1.96
    in
    1.81
    擽
    1.63
    0
    1.55
    an
    1.54
    </b>
    1.52
     sarà
    1.52
     grafico
    1.50
    魠
    1.50
    6
    1.49
    Activations Density 0.028%

    No Known Activations