© 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. 53982
    Prev
    Next
    INDEX
    Explanations

    avoid from X

    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
     ferru
    -0.86
     bords
    -0.80
     superiority
    -0.80
    压制
    -0.80
     pratiquer
    -0.80
     absurdity
    -0.77
     geniuses
    -0.77
    Deaths
    -0.77
    随便
    -0.77
    SIZ
    -0.75
    POSITIVE LOGITS
     лиш
    1.23
     unwanted
    1.23
     unnecessary
    1.13
     irrelevant
    1.03
     distracting
    0.98
     while
    0.91
    setVisibility
    0.88
     certain
    0.87
     mentre
    0.85
    Keep
    0.84
    Activations Density 0.149%

    No Known Activations