© 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. 15199
    Prev
    Next
    INDEX
    Explanations

    Samsung rolls out

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

    The neuron is sensitive to numeric constants in code (i.e. it picks out standalone 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
     it
    -1.69
     if
    -1.65
     only
    -1.45
     by
    -1.44
     who
    -1.27
     plan
    -1.22
     have
    -1.19
    levard
    -1.19
     record
    -1.17
     do
    -1.16
    POSITIVE LOGITS
     gelingt
    1.31
     quedaba
    1.23
    およ
    1.23
     terá
    1.15
     istimewa
    1.13
     龙
    1.13
    Several
    1.13
     trânsito
    1.11
     recém
    1.11
     hảo
    1.10
    Activations Density 0.008%

    No Known Activations