© 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. 102968
    Prev
    Next
    INDEX
    Explanations

    introduces explanatory phrases

    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
     will
    -1.61
     was
    -1.58
     has
    -1.49
     therefore
    -1.44
     have
    -1.44
     still
    -1.44
     thus
    -1.34
    )$.
    -1.34
     took
    -1.33
     remain
    -1.31
    POSITIVE LOGITS
     the
    1.84
    Marcin
    1.53
    你和
    1.44
    ;
    1.33
    蕻
    1.32
     anybody
    1.30
    heden
    1.27
     your
    1.27
     tudi
    1.26
    菈
    1.26
    Activations Density 0.214%

    No Known Activations