© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25961
    Prev
    Next
    INDEX
    Explanations

    entity state or action

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

    The neuron fires on the key topic or subject noun of each passage.

    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
     and
    -1.16
     Außerdem
    -0.96
    hubung
    -0.95
    </h6>
    -0.93
    </h3>
    -0.92
    </h5>
    -0.88
     onbe
    -0.87
    ________
    -0.82
    トル
    -0.82
     bazen
    -0.82
    POSITIVE LOGITS
     of
    3.05
     in
    1.13
     của
    1.12
     from
    1.10
    of
    1.04
    ของ
    1.03
     lietu
    0.96
     ефек
    0.94
    minValue
    0.91
    这件事情
    0.91
    Activations Density 0.057%

    No Known Activations