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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54002
    Prev
    Next
    INDEX
    Explanations

    existence of things

    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_22/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
     adequad
    -1.38
    錶
    -1.35
    粜
    -1.31
     caract
    -1.29
     élimin
    -1.27
    odine
    -1.26
    に挑戦
    -1.22
     exprim
    -1.22
     comportements
    -1.22
     zbo
    -1.21
    POSITIVE LOGITS
     was
    2.23
     is
    2.16
     are
    2.13
     will
    2.08
     have
    1.94
     has
    1.79
     would
    1.77
     still
    1.70
     were
    1.66
     just
    1.65
    Activations Density 0.086%

    No Known Activations