© 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. 34-GEMMASCOPE-RES-131K
    7. 108194
    Prev
    Next
    INDEX
    Explanations

    admitting messing around

    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_34/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
     as
    -2.31
     with
    -2.30
     after
    -2.25
     before
    -2.25
     only
    -2.25
     when
    -2.19
     because
    -2.19
     while
    -2.17
     on
    -2.11
     amidst
    -2.11
    POSITIVE LOGITS
     !!!!
    1.95
     😊
    1.93
    probably
    1.86
     Dinas
    1.84
    primarily
    1.80
    several
    1.79
    perhaps
    1.78
    commonly
    1.77
     zoude
    1.75
     soooo
    1.74
    Activations Density 0.074%

    No Known Activations