© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14443
    Prev
    Next
    INDEX
    Explanations

    dev help links

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

    The neuron activates on numeric tokens (including integers, decimals, and negative‐signed numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     are
    -1.42
     inoltre
    -1.27
     diversas
    -1.27
     vallée
    -1.25
     praktischen
    -1.24
     Entste
    -1.20
     how
    -1.19
     pertanto
    -1.19
    </h4>
    -1.18
     various
    -1.18
    POSITIVE LOGITS
     OUR
    1.28
    所有人都
    1.24
     และ
    1.13
    /"
    1.09
    姽
    1.08
    banez
    1.07
     Cette
    1.06
     all
    1.06
     rekan
    1.06
    fälle
    1.05
    Activations Density 0.233%

    No Known Activations