© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13606
    Prev
    Next
    INDEX
    Explanations

    variable names and code structure

    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
     these
    -1.04
     there
    -1.04
     after
    -1.02
     and
    -0.93
     when
    -0.89
     only
    -0.89
     during
    -0.88
    openSession
    -0.84
     with
    -0.84
     instantly
    -0.81
    POSITIVE LOGITS
    igth
    0.87
    Various
    0.85
    EventListener
    0.85
    ichthys
    0.84
    いろんな
    0.84
     !=
    0.84
     ответа
    0.83
    ఁ
    0.82
     SEVER
    0.81
    xae
    0.81
    Activations Density 0.007%

    No Known Activations