© 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. 119721
    Prev
    Next
    INDEX
    Explanations

    IHC, Kohli, Airtel, Validation

    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
    ⼀
    -2.34
     After
    -2.30
    肛
    -2.28
    傀
    -2.19
    物体
    -2.17
     Since
    -2.17
    重量
    -2.11
    睾
    -2.09
     That
    -2.08
    空白
    -2.08
    POSITIVE LOGITS
    鹛
    2.75
    甞
    2.64
    鴴
    2.59
    鱨
    2.50
    筇
    2.45
    3
    2.42
    埽
    2.38
    拶
    2.36
     jezt
    2.31
    說
    2.28
    Activations Density 0.002%

    No Known Activations