© 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. 36233
    Prev
    Next
    INDEX
    Explanations

    citing references

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

    This neuron fires on the word “see” used as a citation or cross‐reference marker in technical or academic text.

    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
    alties
    -1.73
    ensitive
    -1.73
     ás
    -1.65
    aneity
    -1.59
    Estos
    -1.47
    vereignty
    -1.47
    arised
    -1.45
    terscotch
    -1.44
    Conheça
    -1.44
    urface
    -1.40
    POSITIVE LOGITS
     the
    1.65
     also
    1.34
     vaikka
    1.29
     in
    1.26
    ших
    1.25
     '')
    1.25
    んですけど
    1.21
     např
    1.20
    ]$,
    1.18
     admiten
    1.17
    Activations Density 0.016%

    No Known Activations