© 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. 59928
    Prev
    Next
    INDEX
    Explanations

    in the context of superlatives or locations

    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
    bietet
    -1.55
     yılında
    -1.50
     volando
    -1.48
    wunsch
    -1.45
    worte
    -1.45
    inerario
    -1.41
    Alamat
    -1.40
    følge
    -1.40
    دواج
    -1.39
     rigueur
    -1.39
    POSITIVE LOGITS
    s
    2.34
    as
    2.13
    ly
    2.03
    v
    2.03
    x
    1.93
    j
    1.87
    est
    1.84
     of
    1.82
    ’
    1.77
    y
    1.77
    Activations Density 0.039%

    No Known Activations