© 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. 9831
    Prev
    Next
    INDEX
    Explanations

    monarch, baby, women, gradual, source, unit

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

    The neuron fires on bits of language that give instructions, calls to action, or promotional/evaluative assertions (e.g. directive verbs and upbeat adjectives like “perfect,” “behave,” “team,” etc.).

    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
     Mica
    0.85
     enormously
    0.78
     Ernährung
    0.77
     Algebras
    0.76
    i
    0.76
     BufferedReader
    0.75
    েও
    0.75
    ODE
    0.73
     Simulations
    0.73
     WITHOUT
    0.72
    POSITIVE LOGITS
    𝑐
    0.89
    ş
    0.88
    顾问
    0.86
    我
    0.86
    ศี
    0.82
    Ա
    0.81
    Ві
    0.81
    ار
    0.79
    лон
    0.79
    愿
    0.79
    Activations Density 0.000%

    No Known Activations