© 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. 9221
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    This neuron detects words used as section or listing headings—i.e. standalone title tokens that mark new profile/about-me or article/listing headings.

    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
    barS
    0.41
    {:
    0.38
    TakePhoto
    0.38
     Polaribacter
    0.37
    ┃
    0.37
     OBJECTTYPE
    0.37
    yrıca
    0.36
     DataType
    0.36
    ক্সে
    0.35
    kannt
    0.35
    POSITIVE LOGITS
     .
    0.37
    most
    0.37
     so
    0.36
     de
    0.36
    putting
    0.35
    And
    0.35
    .,
    0.34
    div
    0.34
     sahaja
    0.34
    were
    0.34
    Activations Density 0.285%

    No Known Activations