© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21822
    Prev
    Next
    INDEX
    Explanations

    second week

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

    The neuron fires on longer, standalone content words (multisyllabic base‐forms like “second,” “server,” “developing,” “distribution,” etc.) rather than short function words.

    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
     is
    -2.13
    in
    -1.80
    ly
    -1.59
    between
    -1.59
    _
    -1.58
    is
    -1.57
    to
    -1.55
    mer
    -1.53
    al
    -1.52
    as
    -1.52
    POSITIVE LOGITS
    río
    1.61
     such
    1.59
     while
    1.59
     ==========
    1.55
    richtig
    1.50
    ......”
    1.48
    jangan
    1.44
     firft
    1.42
    రం
    1.41
    daun
    1.39
    Activations Density 0.094%

    No Known Activations