© 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. 42443
    Prev
    Next
    INDEX
    Explanations

    technical keywords and identifiers

    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
     снимка
    -1.43
     Zuschauer
    -1.32
    </strong>
    -1.28
     Ankunft
    -1.28
     freundlichen
    -1.27
    唠
    -1.26
    Canto
    -1.26
     produkty
    -1.23
     Гі
    -1.21
    Ingo
    -1.21
    POSITIVE LOGITS
    verifyException
    1.40
    水泥
    1.36
    offsetof
    1.34
     ApJ
    1.33
     Biennale
    1.33
    Wise
    1.32
    RefNanny
    1.31
    ваку
    1.30
    riceps
    1.30
    luß
    1.30
    Activations Density 0.021%

    No Known Activations