© 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. 629
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on open‐class (content) words—especially longer, less frequent nouns, verbs, and adjectives—while ignoring common function words.

    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
    .
    0.45
     dioxide
    0.42
    および
    0.42
     arba
    0.42
    :
    0.41
     />
    0.40
    ↵↵
    0.40
     components
    0.40
    +
    0.40
    ization
    0.40
    POSITIVE LOGITS
    <unused2146>
    0.47
    <unused1938>
    0.47
    <unused320>
    0.45
    <unused1056>
    0.45
    Liên
    0.44
    誑
    0.44
    కుంది
    0.43
    顰
    0.43
    <unused2190>
    0.43
     চমৎকার
    0.43
    Activations Density 12.640%

    No Known Activations