© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39601
    Prev
    Next
    INDEX
    Explanations

    LayoutInflater, ContextHolder, code snippets

    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
    }
    -2.89
    睒
    -2.45
    是
    -2.36
    IANGLES
    -2.34
    Виды
    -2.27
     of
    -2.23
    ሣ
    -2.19
    鋮
    -2.19
    более
    -2.19
     That
    -2.19
    POSITIVE LOGITS
    텃
    2.70
    ruecos
    2.59
     cherished
    2.52
    "
    2.42
    訁
    2.38
    ll
    2.34
    桖
    2.27
    ⚣
    2.25
    h
    2.23
     troublesome
    2.22
    Activations Density 0.004%

    No Known Activations