© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10662
    Prev
    Next
    INDEX
    Explanations

    mental representations, concepts, essences

    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
    return
    -1.59
    xically
    -1.52
    your
    -1.50
     case
    -1.42
     sorgen
    -1.40
     Inſ
    -1.36
    itemize
    -1.30
     subli
    -1.26
     "\
    -1.22
    errors
    -1.20
    POSITIVE LOGITS
     тільки
    1.66
     only
    1.65
     tumbuhan
    1.47
     etiquetas
    1.42
    ₅
    1.41
     gjennom
    1.35
     Since
    1.35
     Púb
    1.31
     públicas
    1.30
    ₆
    1.30
    Activations Density 0.058%

    No Known Activations