© 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. 95670
    Prev
    Next
    INDEX
    Explanations

    code and proper names

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

    The neuron detects numeric literal tokens (integers or floats) wherever they appear.

    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
    They
    -1.53
    Then
    -1.41
    Currently
    -1.40
     Traducción
    -1.30
    Any
    -1.28
    Should
    -1.24
    Nothing
    -1.23
    MfG
    -1.23
    You
    -1.22
    鸲
    -1.22
    POSITIVE LOGITS
     in
    1.52
     we
    1.41
     at
    1.12
    ですが
    1.11
    sedown
    1.10
    もあり
    1.09
     examines
    1.05
     nonostante
    1.04
     these
    1.03
     examine
    1.02
    Activations Density 0.000%

    No Known Activations