© 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. 36134
    Prev
    Next
    INDEX
    Explanations

    variable declaration keywords like var let

    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
    ཿ
    -1.33
    ཥ
    -1.31
    becomes
    -1.31
    ܇
    -1.30
    hehehe
    -1.27
    휀
    -1.27
    continues
    -1.26
    certainly
    -1.26
     blanches
    -1.25
    蛱
    -1.25
    POSITIVE LOGITS
     even
    1.80
     on
    1.61
     or
    1.58
     in
    1.51
     just
    1.48
     and
    1.47
     there
    1.45
     taking
    1.45
     for
    1.43
     without
    1.40
    Activations Density 0.002%

    No Known Activations