© 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. 66995
    Prev
    Next
    INDEX
    Explanations

    news and events coverage

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

    The neuron fires on the most salient content words—typically key nouns or topic terms that act as headings or subject indicators in a document.

    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
     your
    -1.88
     you
    -1.63
     an
    -1.31
     on
    -1.19
    1
    -1.18
     if
    -1.16
     under
    -1.16
     a
    -1.09
    <tr>
    -1.09
     first
    -1.09
    POSITIVE LOGITS
    mẫu
    1.45
    INDICE
    1.40
    KURZ
    1.36
    nữ
    1.30
     samoz
    1.30
     Tienen
    1.26
    scarpe
    1.25
    lées
    1.23
     equipada
    1.23
    cinq
    1.23
    Activations Density 0.209%

    No Known Activations