© 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. 3925
    Prev
    Next
    INDEX
    Explanations

    code, punctuation, and numbers

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

    The neuron flags tokens that introduce or mark qualifications or constraints in specification‐style text (e.g. stats, as, only, can).

    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
    ्स
    0.96
    ्तिक
    0.82
    ്യം
    0.81
    ς
    0.80
    bursement
    0.74
    edTest
    0.74
    蚪
    0.74
     процессе
    0.73
    ted
    0.73
    মূলক
    0.71
    POSITIVE LOGITS
     keynote
    0.79
    islam
    0.78
    uk
    0.76
     Latvia
    0.76
    q
    0.76
     Argentina
    0.76
     Latino
    0.76
     đẳng
    0.75
    ats
    0.74
     OECD
    0.74
    Activations Density 0.000%

    No Known Activations