© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78523
    Prev
    Next
    INDEX
    Explanations

    this kind of

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on generic category phrases that label something as “this kind of,” “this type of,” or “this sort of” thing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     maniere
    -1.70
     différents
    -1.70
    various
    -1.56
     impecable
    -1.55
     ulike
    -1.55
     protokol
    -1.53
    keteers
    -1.53
     siè
    -1.53
     pernic
    -1.52
     plafon
    -1.52
    POSITIVE LOGITS
     thing
    2.67
     stuff
    2.19
     situation
    1.93
     information
    1.91
     activity
    1.82
     things
    1.68
     work
    1.63
     thinking
    1.61
     analysis
    1.60
     an
    1.55
    Activations Density 0.031%

    No Known Activations