© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12013
    Prev
    Next
    INDEX
    Explanations

    adjustments or variations

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

    The neuron broadly fires on common high-frequency function words (articles, pronouns, prepositions, auxiliaries, 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_31_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
    </b>
    0.90
    ``
    0.70
    </sup>
    0.63
    ‍
    0.63
    $...
    0.63
    `
    0.63
    '...
    0.62
    以下
    0.60
    CreateWindow
    0.60
    `.
    0.58
    POSITIVE LOGITS
     cialis
    1.16
     http
    1.05
     viagra
    0.89
     ción
    0.89
     nike
    0.88
     tions
    0.85
     https
    0.84
    ");//
    0.82
     
    0.82
     
    0.81
    Activations Density 0.856%

    No Known Activations