© 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. 65274
    Prev
    Next
    INDEX
    Explanations

    code snippets and foreign words

    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
     still
    -1.64
    仍然
    -1.41
     when
    -1.38
    crollView
    -1.34
    “,
    -1.34
    lysm
    -1.34
    },
    -1.31
    璜
    -1.31
    ”,
    -1.30
     time
    -1.28
    POSITIVE LOGITS
     are
    1.66
     will
    1.64
     المختلفة
    1.45
     seperti
    1.41
     from
    1.30
     Hence
    1.29
     כמו
    1.27
    !
    1.23
     like
    1.20
    показа
    1.19
    Activations Density 0.004%

    No Known Activations