© 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. 8687
    Prev
    Next
    INDEX
    Explanations

    write a function

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

    The neuron detects link-style continuation prompts or calls to action (e.g. “click title for more details,” “read more,” 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
    4
    0.67
    View
    0.66
    Continue
    0.66
    Ari
    0.66
    Read
    0.65
    Hart
    0.65
    2
    0.63
    K
    0.63
    Text
    0.63
     Ari
    0.62
    POSITIVE LOGITS
     коэффици
    0.65
    îte
    0.63
     municípios
    0.60
     සහිත
    0.59
    inskii
    0.59
    ্ে
    0.58
    owymi
    0.58
     каждо
    0.57
     επίπε
    0.57
     localidades
    0.57
    Activations Density 0.055%

    No Known Activations