© 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. 63498
    Prev
    Next
    INDEX
    Explanations

    personal identification PIN

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

    The neuron strongly activates on mentions of device login methods—especially numeric PINs or pattern-based locks.

    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
    Thirty
    -0.84
    helps
    -0.78
     HELP
    -0.77
    Help
    -0.76
    ⽼
    -0.76
    Helping
    -0.75
    suggest
    -0.74
    helping
    -0.73
    ISTRY
    -0.72
     lone
    -0.71
    POSITIVE LOGITS
     PIN
    3.23
     pin
    2.67
    PIN
    2.61
    pin
    2.25
     Pin
    2.22
    Pin
    2.20
     code
    1.99
     pins
    1.72
    code
    1.69
     codes
    1.67
    Activations Density 0.036%

    No Known Activations