© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 539
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on isolated single uppercase letters (i.e. single‐character capital tokens).

    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
     EVAL
    0.26
    OL
    0.25
     commonly
    0.25
    и
    0.25
    xf
    0.25
    OC
    0.24
    xc
    0.24
     ICD
    0.23
    IG
    0.23
    IC
    0.23
    POSITIVE LOGITS
    ن
    0.38
    或許
    0.34
    یر
    0.34
    م
    0.33
     ήταν
    0.30
    嗎
    0.30
    و
    0.30
    ير
    0.30
     Nhưng
    0.29
    sächlich
    0.29
    Activations Density 0.000%

    No Known Activations