© 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. 54454
    Prev
    Next
    INDEX
    Explanations

    but

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

    The neuron activates on standalone numbers (numeric tokens).

    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
    歟
    -1.27
     alojamientos
    -1.18
     célèbre
    -1.16
     postales
    -1.13
     accedi
    -1.11
    冷たい
    -1.10
    🤐
    -1.10
     mourir
    -1.09
    område
    -1.09
     illustre
    -1.09
    POSITIVE LOGITS
     have
    2.11
     had
    1.80
     I
    1.80
     want
    1.47
     know
    1.44
     did
    1.41
     gave
    1.40
     went
    1.38
     knew
    1.36
     understand
    1.35
    Activations Density 0.050%

    No Known Activations