© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98508
    Prev
    Next
    INDEX
    Explanations

    different kinds/types

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

    The neuron fires on adjectives (and related determiners) that signal variation or distinction—e.g. “different,” “various,” “distinct,” “varying,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     alcuni
    -1.34
    setAlpha
    -1.20
     précédent
    -1.18
     někter
    -1.17
     itself
    -1.17
     anymore
    -1.12
    tische
    -1.10
     savent
    -1.10
    uded
    -1.09
     alcune
    -1.09
    POSITIVE LOGITS
     types
    1.23
     sets
    1.13
     different
    1.10
     kinds
    1.04
     their
    1.04
     amounts
    1.03
     uses
    1.02
    L
    1.01
     set
    1.00
     sized
    0.99
    Activations Density 0.081%

    No Known Activations