© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9369
    Prev
    Next
    INDEX
    Explanations

    write, speak, solve, continue

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

    The neuron fires on domain‐specific or technical content words—especially key steps, components, and parameters in procedural or instructional text.

    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
    oses
    0.55
    ;(
    0.53
    </i>
    0.52
    ities
    0.52
    Hmm
    0.52
    L
    0.52
    hoes
    0.51
    D
    0.50
    ;)
    0.49
     thereof
    0.49
    POSITIVE LOGITS
     Latinoamérica
    0.60
     στο
    0.59
     racconto
    0.59
     bequest
    0.59
    вний
    0.58
     groundbreaking
    0.56
     Futuristic
    0.55
    हायला
    0.55
     trailbl
    0.55
     Được
    0.54
    Activations Density 0.003%

    No Known Activations