© 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. 38808
    Prev
    Next
    INDEX
    Explanations

    anemia, Chavez, Giuliani, Archer

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

    The neuron strongly activates on multi-syllable proper names and specialized nouns (e.g. “Trampoline,” “Giuliani,” “Chávez,” “Aquarius,” “anemia”).

    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
     soo
    -2.55
    ﮧ
    -2.45
    ῞
    -2.42
    indelijk
    -2.38
    IANGLES
    -2.36
     ३
    -2.36
     WITH
    -2.36
    ll
    -2.34
     avere
    -2.27
     öv
    -2.27
    POSITIVE LOGITS
    .
    3.08
    the
    2.55
    <
    2.23
    ;
    2.08
    %
    2.02
    </td>
    2.02
    such
    1.99
    «
    1.98
    us
    1.98
     \
    1.98
    Activations Density 0.007%

    No Known Activations