© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    key-value pairs or attribute assignments

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

    The neuron detects numeric tokens (especially floating‐point and integer literals).

    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
    rizona
    -1.36
    ‗
    -1.20
    ``,
    -1.16
    fty
    -1.13
    \%,
    -1.10
    »,
    -1.10
    élé
    -1.09
    amom
    -1.09
    rror
    -1.09
    pica
    -1.09
    POSITIVE LOGITS
     despite
    1.12
    );
    1.10
     not
    1.09
     both
    1.07
    Probl
    1.05
     very
    1.05
     pudesse
    1.05
    Pemer
    1.05
    :
    1.04
    ஒ
    1.02
    Activations Density 0.015%

    No Known Activations