© 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. 22-GEMMASCOPE-RES-131K
    7. 38565
    Prev
    Next
    INDEX
    Explanations

    contact phone number email office

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

    The neuron flags contact‐oriented metadata (e.g. “Contact,” “Information,” and adjacent phone/address details).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    licante
    -1.52
    −/−
    -1.49
    ご購入
    -1.22
     bakso
    -1.19
    madeus
    -1.18
     warung
    -1.14
    𝑄
    -1.10
     bukit
    -1.09
     bandung
    -1.09
    っか
    -1.09
    POSITIVE LOGITS
     at
    1.77
     contact
    1.73
     phone
    1.55
     can
    1.30
     telephone
    1.27
     services
    1.22
     office
    1.20
     if
    1.16
     their
    1.15
     email
    1.14
    Activations Density 0.011%

    No Known Activations