© 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. 10-GEMMASCOPE-RES-131K
    4. 90646
    Prev
    Next
    INDEX
    Explanations

    academic degrees

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

    The neuron fires on numeric values with decimal points (i.e. measurements or quantities expressed as x.y).

    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
     these
    -1.63
     moim
    -1.47
     небольшие
    -1.37
     leſs
    -1.37
     wszyscy
    -1.37
    笆
    -1.36
     nuov
    -1.35
     этих
    -1.35
     поэтому
    -1.34
    −/−
    -1.32
    POSITIVE LOGITS
     at
    1.70
     during
    1.64
     there
    1.59
     There
    1.59
     by
    1.58
     including
    1.57
     as
    1.51
     in
    1.51
     if
    1.51
     here
    1.48
    Activations Density 0.198%

    No Known Activations