© 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. 22-GEMMASCOPE-RES-131K
    7. 79837
    Prev
    Next
    INDEX
    Explanations

    quantities and values

    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_22/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
    </u>
    -1.44
    𝑛
    -1.26
    )]
    -1.26
    Ꮈ
    -1.23
    %',
    -1.23
    𝑚
    -1.15
    𝑙
    -1.15
     \%
    -1.15
    出る
    -1.13
    ˃
    -1.13
    POSITIVE LOGITS
     of
    2.59
     for
    1.43
    嫉
    1.36
    และ
    1.25
    ﾆ
    1.20
    を
    1.16
    弱点
    1.13
     persoonlijke
    1.13
     Mittelpunkt
    1.13
     또는
    1.13
    Activations Density 0.044%

    No Known Activations