© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    twitter

    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
     atau
    -2.95
    倥
    -2.55
     alebo
    -2.55
     eller
    -2.47
    s
    -2.30
    蹚
    -2.20
    埽
    -2.16
    揼
    -2.14
    铩
    -2.05
     человек
    -2.03
    POSITIVE LOGITS
    This
    2.52
    ◱
    2.23
     ursprüng
    2.22
     Vordergrund
    2.20
     gesamte
    2.19
     Fully
    2.16
    皺
    2.16
     Effectively
    2.14
    }
    2.13
    -
    2.09
    Activations Density 0.002%

    No Known Activations