© 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. 39032
    Prev
    Next
    INDEX
    Explanations

    technical questions

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

    The neuron strongly activates on the character sequence “ago” within tokens.

    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
    and
    -2.92
    to
    -2.42
    Four
    -2.22
    $
    -2.20
    Eight
    -2.17
     inga
    -2.17
    an
    -2.16
     determining
    -2.14
     If
    -2.08
    with
    -2.06
    POSITIVE LOGITS
     เพราะ
    2.31
     peculiarly
    2.31
    ㉗
    2.30
     
    2.19
     marvelous
    2.16
    tarjetas
    2.14
    </sup>
    2.11
     normalerweise
    2.08
     Internation
    2.05
     Impressive
    2.03
    Activations Density 0.143%

    No Known Activations