© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13655
    Prev
    Next
    INDEX
    Explanations

    San Francisco

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

    The neuron fires on occurrences of the place name “San Francisco.”

    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
     erhi
    -2.55
    ꦧ
    -2.45
     reduziert
    -2.41
    或是
    -2.39
     белого
    -2.36
    不管是
    -2.31
     ceaseless
    -2.28
     wichtigsten
    -2.25
     colocando
    -2.25
    或者
    -2.17
    POSITIVE LOGITS
    </td>
    3.19
    </h5>
    2.73
    .
    2.67
    </h6>
    2.53
    }$,
    2.28
     */
    2.23
     foi
    2.22
     []
    2.20
     \
    2.19
     lige
    2.17
    Activations Density 0.004%

    No Known Activations