© 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. 41933
    Prev
    Next
    INDEX
    Explanations

    doi urls

    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
    If
    -2.41
    When
    -2.16
    9
    -2.05
    Most
    -1.91
    In
    -1.89
    The
    -1.87
    Even
    -1.84
     provide
    -1.82
     maintain
    -1.80
    \
    -1.80
    POSITIVE LOGITS
    liegende
    1.59
    jalan
    1.57
     aisladas
    1.56
     interesantes
    1.55
    AtA
    1.51
    蹰
    1.50
     jugadores
    1.48
     hígado
    1.47
     yalnız
    1.45
    Eccles
    1.44
    Activations Density 0.005%

    No Known Activations