© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54408
    Prev
    Next
    INDEX
    Explanations

    help or difficulty with a service

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

    This neuron activates on numeric tokens and number-like strings (e.g. counts, measurements, version numbers, or other digit sequences).

    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
    Their
    -1.59
     Their
    -1.25
     rodrigo
    -1.13
     foon
    -1.10
     capuz
    -1.09
     moletom
    -1.09
     kada
    -1.08
     puto
    -1.08
     ronaldo
    -1.07
     automobili
    -1.05
    POSITIVE LOGITS
     or
    2.20
     your
    1.94
     you
    1.59
     please
    1.51
     our
    1.47
     yourself
    1.31
     this
    1.23
     или
    1.22
     feel
    1.20
     пожалуйста
    1.17
    Activations Density 0.049%

    No Known Activations