© 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. 104365
    Prev
    Next
    INDEX
    Explanations

    units and measurements

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

    This neuron activates on numeric measurement tokens (numerals and decimal values).

    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
    Quais
    -1.14
    Acab
    -1.10
    Confira
    -1.06
    𝘺
    -1.03
    镑
    -1.02
    Otra
    -1.02
     "..\..\..\
    -1.02
    蛧
    -1.01
     consultato
    -1.01
    Estar
    -1.00
    POSITIVE LOGITS
     in
    1.33
     bisous
    1.13
    melidir
    1.10
     delicioso
    1.09
     első
    1.04
     honneur
    1.00
     personnalisées
    0.99
     eredeti
    0.98
     premiers
    0.98
     otthon
    0.98
    Activations Density 0.064%

    No Known Activations