© 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. 68556
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
     what
    -1.38
     because
    -1.32
     not
    -1.28
     one
    -1.25
     when
    -1.20
     three
    -1.19
     this
    -1.18
     only
    -1.15
     people
    -1.15
     from
    -1.13
    POSITIVE LOGITS
     vastly
    1.19
    Its
    1.17
     flashy
    1.15
     ridiculously
    1.15
     ludicrous
    1.12
     unbelievably
    1.12
     flamboyant
    1.11
     wondrous
    1.09
    usually
    1.08
     parfois
    1.08
    Activations Density 0.005%

    No Known Activations