© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64775
    Prev
    Next
    INDEX
    Explanations

    all and its following words

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

    The neuron fires on occurrences of the token “all” (in various capitalizations), whether standing alone or as the first word in multiword names.

    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
    私も
    -0.80
    あった
    -0.78
    érieurs
    -0.76
    KeyEvent
    -0.75
    ленное
    -0.75
    ია
    -0.75
    ленность
    -0.74
     disgraceful
    -0.74
    ง่าย
    -0.74
     depra
    -0.72
    POSITIVE LOGITS
    ying
    1.26
    uding
    1.20
     sorts
    1.16
    usive
    1.16
    oted
    1.15
    ured
    1.10
     manner
    1.09
     kinds
    1.08
    uded
    1.07
    spice
    1.07
    Activations Density 0.076%

    No Known Activations