© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72387
    Prev
    Next
    INDEX
    Explanations

    and/or

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

    The neuron identifies list‐style enumeration cues—punctuation (commas), conjunctions like “and/or,” and numeric markers that signal items in a list.

    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
     CLAIMS
    -1.42
    imee
    -1.33
    allowing
    -1.30
     sábado
    -1.29
    potentially
    -1.28
    
    -1.27
     yogur
    -1.27
     permettant
    -1.26
    specially
    -1.25
     EFFECTS
    -1.22
    POSITIVE LOGITS
     and
    1.28
     to
    1.27
     with
    1.20
     without
    1.19
     any
    1.19
     Two
    1.16
     K
    1.13
     by
    1.13
     children
    1.13
     Z
    1.11
    Activations Density 0.002%

    No Known Activations