© 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. 10-GEMMASCOPE-RES-131K
    4. 14918
    Prev
    Next
    INDEX
    Explanations

    axioms and quotient

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

    The neuron activates strongly on occurrences of the term “quotient” (i.e. references to mathematical quotients).

    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
    -2.78
    i
    -2.72
     namorados
    -2.69
     sapatos
    -2.55
    1
    -2.52
    疍
    -2.47
    糴
    -2.45
    
    -2.44
     pantal
    -2.42
    グルト
    -2.42
    POSITIVE LOGITS
    '
    3.19
     of
    2.48
    </em>
    2.44
    .\\
    2.33
    ほか
    2.25
    ');
    2.23
    ).
    2.22
    providedIn
    2.19
    </td>
    2.17
    </h4>
    2.14
    Activations Density 0.001%

    No Known Activations