© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42638
    Prev
    Next
    INDEX
    Explanations

    import url

    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
     decorativas
    -1.30
    攰
    -1.23
     deliciosos
    -1.23
    いかがでしたか
    -1.22
     signs
    -1.22
     plantes
    -1.22
    midt
    -1.19
    arlos
    -1.17
    昔から
    -1.16
     bessere
    -1.16
    POSITIVE LOGITS
     perché
    1.44
     apenas
    1.44
     only
    1.38
     karena
    1.34
     именно
    1.29
     два
    1.23
     porque
    1.23
     when
    1.22
    ônia
    1.21
     hanya
    1.20
    Activations Density 0.120%

    No Known Activations