© 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. 71289
    Prev
    Next
    INDEX
    Explanations

    object creation and automation

    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
     tudi
    -1.24
    __":
    -1.16
     jego
    -1.15
    Даже
    -1.14
    \":
    -1.14
     yine
    -1.14
    zwischen
    -1.14
     págs
    -1.13
    Эти
    -1.13
    Sri
    -1.13
    POSITIVE LOGITS
     it
    1.68
     this
    1.46
     what
    1.34
     whom
    1.31
     einst
    1.24
     different
    1.23
     who
    1.14
    smh
    1.14
     before
    1.13
     how
    1.09
    Activations Density 0.082%

    No Known Activations