© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    actions with 'up' or 'on'

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

    The neuron strongly activates on tokens ending in “-ing,” i.e. gerunds or present‐participle forms.

    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
     unscathed
    0.54
    ствовали
    0.54
    ство
    0.52
    pane
    0.51
    stricken
    0.50
    ु
    0.49
     summar
    0.49
    ‿
    0.49
    places
    0.49
    ствуют
    0.49
    POSITIVE LOGITS
    č
    0.54
     animaux
    0.48
    원
    0.47
     kinderen
    0.47
     chiens
    0.46
    /
    0.45
     Plants
    0.44
    ச
    0.43
    વન
    0.43
    並沒有
    0.43
    Activations Density 0.000%

    No Known Activations