© 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. 40518
    Prev
    Next
    INDEX
    Explanations

    specifications

    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
    新
    -2.59
    「
    -2.30
    🌼
    -2.14
     When
    -2.05
    when
    -2.03
    </i>
    -2.00
     With
    -1.99
    今
    -1.96
     If
    -1.89
    رحلة
    -1.89
    POSITIVE LOGITS
     rozpoczę
    2.53
    ‪.‬‬
    2.50
    五六
    2.50
    其妙
    2.41
    −/−
    2.33
     antique
    2.27
    ﱠ
    2.25
    ‌.
    2.20
    。“
    2.17
    很快就
    2.16
    Activations Density 0.003%

    No Known Activations