© 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. 15169
    Prev
    Next
    INDEX
    Explanations

    code blocks and file names

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

    The neuron strongly fires on spammy or promotional header text—i.e. ad-style pitches for products or services.

    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
     Charity
    0.80
    쎈
    0.74
     a
    0.74
     charity
    0.73
     coolant
    0.72
     coastal
    0.71
     postal
    0.71
     river
    0.70
     artery
    0.70
     kinetic
    0.69
    POSITIVE LOGITS
    шел
    0.94
     utilisateurs
    0.92
    ◐
    0.91
    Psal
    0.89
    🎱
    0.89
    🏈
    0.89
    SIM
    0.88
    👾
    0.88
    REFLECTION
    0.88
    🎆
    0.88
    Activations Density 0.001%

    No Known Activations