© 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. 95579
    Prev
    Next
    INDEX
    Explanations

    current state or configuration

    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
     MUCH
    -0.95
    lių
    -0.91
    vær
    -0.88
    萘
    -0.87
    IVAL
    -0.86
     pinto
    -0.86
    atele
    -0.84
     Нови
    -0.83
    Literals
    -0.83
    ORUM
    -0.83
    POSITIVE LOGITS
     existing
    1.34
     currently
    1.25
     already
    1.19
     status
    1.13
     it
    1.09
     configuration
    1.08
     previously
    1.04
     current
    1.03
     set
    1.03
     automatic
    1.02
    Activations Density 0.079%

    No Known Activations