© 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. 10-GEMMASCOPE-RES-131K
    7. 61403
    Prev
    Next
    INDEX
    Explanations

    emphasis and confirmation

    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
    Инг
    -1.66
    ؎
    -1.55
    🌫
    -1.50
     asesinado
    -1.45
     něm
    -1.45
    centaje
    -1.43
    "}
    -1.43
    )}
    -1.41
    ांकि
    -1.40
    挥手
    -1.38
    POSITIVE LOGITS
    is
    1.84
    n
    1.71
    $
    1.68
     of
    1.64
    -*
    1.63
    one
    1.58
    id
    1.58
    al
    1.57
     other
    1.56
    for
    1.51
    Activations Density 0.002%

    No Known Activations