© 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. 68535
    Prev
    Next
    INDEX
    Explanations

    items connected by 'and'

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

    The neuron flags the main domain‐specific content words—i.e. the key technical nouns that carry the core topic information.

    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
     in
    -3.20
     on
    -2.45
     of
    -2.45
     (
    -2.42
     at
    -2.41
     when
    -2.27
     for
    -2.16
     after
    -2.13
     will
    -1.95
     by
    -1.86
    POSITIVE LOGITS
     and
    7.38
    และ
    3.23
    や
    2.39
     både
    2.28
     மற்றும்
    2.20
     allerlei
    2.19
     zowel
    2.14
     ...........
    2.03
    owm
    2.02
     sekä
    1.98
    Activations Density 1.729%

    No Known Activations