© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 351
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens containing a hyphen (i.e. fragments or codes that end with “-”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     induc
    0.20
     anormal
    0.19
     reduc
    0.19
    ُ
    0.19
    ylate
    0.19
     accolade
    0.19
     maked
    0.18
     a
    0.18
     а
    0.18
     tempr
    0.18
    POSITIVE LOGITS
    এর
    0.30
    R
    0.28
    J
    0.28
    T
    0.27
     kuten
    0.27
    W
    0.27
     También
    0.26
     এছাড়াও
    0.26
    K
    0.25
    A
    0.24
    Activations Density 0.594%

    No Known Activations