© 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. 72653
    Prev
    Next
    INDEX
    Explanations

    Nogier, noggin, IFMA, Risk

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

    variations of the word "Noggin" or "Nog" across different contexts.

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

    The neuron fires on any occurrence of the substring “nog” within a token.

    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
    at
    -2.97
    as
    -2.78
    حتى
    -2.66
    e
    -2.61
    Ꮽ
    -2.44
     been
    -2.25
     教室
    -2.19
    枼
    -2.19
    atação
    -2.11
     sayfa
    -2.11
    POSITIVE LOGITS
    ’
    2.47
    娲
    2.28
    …"
    2.28
     ähnliche
    2.22
    carnated
    2.13
    ጵ
    2.09
    nA
    2.09
     evitando
    2.08
     leichte
    2.08
    よって
    2.06
    Activations Density 0.001%

    No Known Activations