© 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. 39389
    Prev
    Next
    INDEX
    Explanations

    in order, in writing

    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
    What
    -1.93
    From
    -1.81
    When
    -1.73
    man
    -1.73
    Since
    -1.69
    他にも
    -1.59
    が
    -1.59
     Surprisingly
    -1.56
     größeren
    -1.56
    Before
    -1.55
    POSITIVE LOGITS
    螃
    2.11
     erhi
    2.02
    苼
    1.95
     raiſ
    1.90
     créer
    1.88
     a
    1.79
    ᠌
    1.77
    僦
    1.77
     verhind
    1.72
    klassi
    1.68
    Activations Density 0.062%

    No Known Activations