© 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. 119840
    Prev
    Next
    INDEX
    Explanations

    ranging from

    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
    iapkan
    -1.69
    dziew
    -1.62
    <bos>
    -1.61
    勛
    -1.59
    憫
    -1.52
     Although
    -1.51
     When
    -1.51
     Despite
    -1.50
     Apparently
    -1.48
    Ironically
    -1.47
    POSITIVE LOGITS
     μὲν
    1.64
     некоторые
    1.63
    阂
    1.58
    .'
    1.55
    苳
    1.54
    endfor
    1.52
    𐀀
    1.50
     a
    1.48
     estos
    1.44
     anf
    1.44
    Activations Density 0.016%

    No Known Activations