© 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. 85874
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The main thing this neuron does is find phone‐number–style digit sequences.

    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
     procurando
    -1.63
    </sup>
    -1.63
    //=
    -1.50
     participado
    -1.50
     такими
    -1.49
    }=\
    -1.48
    }$
    -1.45
     eliminado
    -1.45
    を選
    -1.44
     anunciado
    -1.43
    POSITIVE LOGITS
     Tentang
    1.55
     the
    1.55
    m
    1.52
     Internasional
    1.51
    𞤢
    1.50
     Tasche
    1.47
     vengono
    1.44
    🕗
    1.42
     menyiapkan
    1.38
    āna
    1.38
    Activations Density 0.039%

    No Known Activations