© 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. 10688
    Prev
    Next
    INDEX
    Explanations

    Code or specific notation

    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
    蓴
    -2.34
    ⬮
    -2.20
     欣赏
    -2.14
     记
    -2.05
    可以通过
    -1.95
    
    -1.92
     débil
    -1.88
     tepat
    -1.83
     喜欢
    -1.82
    ("")]
    -1.80
    POSITIVE LOGITS
    }
    2.63
    1
    2.45
    ates
    2.41
    2
    2.38
    ти
    2.28
    <
    2.23
    it
    2.11
    ни
    2.09
    </
    2.03
    you
    1.95
    Activations Density 0.010%

    No Known Activations