© 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. 10-GEMMASCOPE-RES-131K
    7. 7132
    Prev
    Next
    INDEX
    Explanations

    allele-specific hybridization

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

    programming-related identifier names or technical terms in code and technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects adjective tokens (words labeled with the “JJ” part‐of‐speech tag, shown here as “_JJ”).

    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
    \
    -2.64
    即便是
    -2.48
    the
    -2.48
     Brought
    -2.41
    t
    -2.33
    ные
    -2.23
    —-
    -2.23
     the
    -2.23
    },
    -2.22
    骉
    -2.19
    POSITIVE LOGITS
     rajut
    2.48
     baju
    2.47
     musíte
    2.44
    驁
    2.44
     budete
    2.44
     musuh
    2.42
    떳
    2.39
    してくれた
    2.38
    鹮
    2.38
    Ruju
    2.36
    Activations Density 0.075%

    No Known Activations