© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38455
    Prev
    Next
    INDEX
    Explanations

    actions followed by specifics

    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
     or
    -2.59
     this
    -2.23
     after
    -2.16
     when
    -2.13
     other
    -2.06
     as
    -2.02
     which
    -1.91
     it
    -1.84
     before
    -1.80
     additional
    -1.69
    POSITIVE LOGITS
    mainly
    2.48
    primarily
    2.41
     både
    2.38
    both
    2.11
     principalement
    2.06
    mostly
    2.05
     zowel
    1.98
    particularly
    1.95
     principalmente
    1.81
     predominantly
    1.79
    Activations Density 0.125%

    No Known Activations