© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112770
    Prev
    Next
    INDEX
    Explanations

    rules and statements

    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
     its
    -1.42
     very
    -1.38
     姆
    -1.36
     important
    -1.31
     such
    -1.29
     same
    -1.27
     interesting
    -1.25
     insisting
    -1.20
     that
    -1.19
     careful
    -1.19
    POSITIVE LOGITS
     beeintr
    1.49
    enné
    1.24
     recordó
    1.23
     entrepre
    1.22
     añadió
    1.16
     celebró
    1.14
     voorbij
    1.13
     cerró
    1.12
    россий
    1.10
     ailing
    1.10
    Activations Density 1.153%

    No Known Activations