© 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. 10-GEMMASCOPE-RES-131K
    4. 65518
    Prev
    Next
    INDEX
    Explanations

    discussion, exhibition, soon, open

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

    The neuron strongly activates on title‐style or named‐entity phrases—i.e. multiword, capitalized headings or proper 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_10/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
    )])
    -1.50
    iters
    -1.49
     και
    -1.48
     }_{
    -1.45
    }[
    -1.43
    erráneo
    -1.39
    )]);
    -1.39
     هستند
    -1.38
    )):
    -1.37
    )}}
    -1.37
    POSITIVE LOGITS
    \&
    1.43
    \\
    1.42
     richtigen
    1.40
    --
    1.37
    isinin
    1.36
     również
    1.35
     Например
    1.34
    '
    1.34
     menschlichen
    1.34
     like
    1.34
    Activations Density 0.099%

    No Known Activations