© 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. 6
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to the subword “ident,” i.e. fragments of words related to identification or identity.

    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
    andelion
    0.44
     Hfn
    0.43
    рована
    0.43
    Comparator
    0.42
    mainwindow
    0.41
    UnitTest
    0.40
    ὰ
    0.40
    ając
    0.39
    oggler
    0.39
     rjf
    0.39
    POSITIVE LOGITS
     entrust
    0.43
     illetve
    0.38
     sh
    0.38
    ↵
    0.37
    橐
    0.37
     minors
    0.37
     stylish
    0.36
    这一
    0.36
    튠
    0.36
     comparten
    0.36
    Activations Density 0.000%

    No Known Activations