© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110982
    Prev
    Next
    INDEX
    Explanations

    action followed by preposition

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

    This neuron detects tokens that appear in page titles or headlines (i.e. prominent, capitalized heading text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     czter
    -1.25
     оригі
    -1.24
     것입니다
    -1.22
     oczeki
    -1.22
     відео
    -1.21
     відповід
    -1.19
     promociones
    -1.19
    dekat
    -1.19
     their
    -1.18
    ところは
    -1.18
    POSITIVE LOGITS
    が
    1.50
    を
    1.24
    の
    1.23
    ка
    1.19
    から
    1.12
     msglen
    1.11
     ❤
    1.09
     👀
    1.09
    опера
    1.09
     основ
    1.08
    Activations Density 0.171%

    No Known Activations