© 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. 722
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on empty or whitespace‐only tokens (i.e. blank lines or paragraph breaks).

    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
    :
    0.64
     —
    0.52
    —
    0.52
    ־
    0.52
    ––
    0.49
     replete
    0.49
    barui
    0.48
     sejumlah
    0.46
    –
    0.46
    ː
    0.45
    POSITIVE LOGITS
     Also
    1.09
     Также
    1.02
     Anyways
    1.02
     Basically
    0.98
     aswell
    0.97
     Вообще
    0.96
     Honestly
    0.89
     मैं
    0.88
     Myself
    0.87
     제가
    0.86
    Activations Density 0.001%

    No Known Activations