© 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. 34-GEMMASCOPE-RES-131K
    7. 65793
    Prev
    Next
    INDEX
    Explanations

    function unit void ignores

    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_34/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
     nothing
    -1.66
    nothing
    -1.59
     nichts
    -1.51
    Nothing
    -1.51
     Nothing
    -1.48
     ничего
    -1.45
    NOTHING
    -1.18
     NOTHING
    -1.16
     niets
    -1.13
     rien
    -1.05
    POSITIVE LOGITS
     ()
    1.59
     (),
    1.57
     ();
    1.34
     ();
    1.25
    ()
    1.25
     ().
    1.25
     ()
    1.20
    ()
    1.18
    (),
    1.16
     ())
    1.02
    Activations Density 0.031%

    No Known Activations