© 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. 13516
    Prev
    Next
    INDEX
    Explanations

    More information about

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

    The neuron flags numeric tokens (especially multi‐digit 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_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
     hará
    -1.37
    皆さま
    -1.30
    
    -1.30
     ARISING
    -1.30
    Their
    -1.29
    みなさま
    -1.28
    久しぶりに
    -1.27
     Normalmente
    -1.27
    Viitteet
    -1.26
    久しぶりの
    -1.26
    POSITIVE LOGITS
     this
    2.20
     how
    2.02
     our
    1.91
     of
    1.84
     these
    1.45
     onsdag
    1.31
    닮
    1.31
     and
    1.31
     alebo
    1.24
     lagar
    1.19
    Activations Density 0.013%

    No Known Activations