© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41213
    Prev
    Next
    INDEX
    Explanations

    "its" followed by descriptive adjectives/nouns

    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
     such
    -1.91
     what
    -1.80
     requires
    -1.42
     when
    -1.34
     it
    -1.33
     in
    -1.32
     usually
    -1.30
    歳の
    -1.29
    acije
    -1.26
    what
    -1.24
    POSITIVE LOGITS
    tedrale
    1.51
    ,
    1.34
     洗濯
    1.31
     novamente
    1.31
     trotz
    1.31
    ните
    1.31
    撂
    1.28
    iner
    1.27
     tollen
    1.27
     трех
    1.27
    Activations Density 0.016%

    No Known Activations