© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33687
    Prev
    Next
    INDEX
    Explanations

    Makan, Makanan, Manfaat

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

    The neuron fires on the first key content word (the primary noun or topic term) that begins an answer.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    P
    -1.27
    E
    -1.26
     to
    -1.25
    S
    -1.14
     P
    -1.13
     O
    -1.09
     „
    -1.08
    R
    -1.07
    T
    -1.06
     ,,
    -1.05
    POSITIVE LOGITS
    Berat
    1.51
    Makanan
    1.40
    Penjelasan
    1.38
    Terima
    1.35
    Bahkan
    1.32
    Iya
    1.32
    Baru
    1.30
    Makan
    1.28
    Manfaat
    1.27
    Sekarang
    1.27
    Activations Density 0.029%

    No Known Activations