© 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. 34-GEMMASCOPE-RES-131K
    7. 107218
    Prev
    Next
    INDEX
    Explanations

    phone and yellow pages listings

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

    The main thing this neuron does is detect “lookup” or “search”–style terms (e.g. look, search) and related info-source nouns (directory, phonebook).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    semp
    -0.75
    สด
    -0.75
    补
    -0.74
    lecteur
    -0.73
    廟
    -0.71
     FRES
    -0.69
    setFocusable
    -0.68
     někter
    -0.67
    fires
    -0.67
     frais
    -0.67
    POSITIVE LOGITS
     phone
    2.20
     Yellow
    2.05
     yellow
    1.92
     telephone
    1.88
    Yellow
    1.80
    yellow
    1.70
     Phone
    1.67
    phone
    1.58
     телефон
    1.54
    YELLOW
    1.52
    Activations Density 0.022%

    No Known Activations