© 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. 34-GEMMASCOPE-RES-131K
    7. 58622
    Prev
    Next
    INDEX
    Explanations

    past

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

    The neuron fires most strongly on the first content word of each new text block (i.e. sentence or paragraph openers).

    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
     swiftly
    -1.34
     both
    -1.30
     steadily
    -1.27
     supremely
    -1.23
     utterly
    -1.19
     their
    -1.18
     lavish
    -1.18
     considerably
    -1.14
     undeniably
    -1.13
     superbly
    -1.13
    POSITIVE LOGITS
     SPECIFIC
    1.17
     THROUGH
    1.03
     REQU
    1.03
    grä
    1.02
    ,;
    1.01
     Dinas
    1.00
     souvent
    1.00
    hater
    0.98
     DIFFERENT
    0.98
    ੲ
    0.98
    Activations Density 0.004%

    No Known Activations