© 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. 34-GEMMASCOPE-RES-131K
    7. 49712
    Prev
    Next
    INDEX
    Explanations

    authenticity and authentication

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

    The neuron activates on word stems and tokens related to “authent…” (authentication/authenticity) across various contexts.

    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
     getEmail
    -0.75
    Ἄ
    -0.73
    Aper
    -0.72
     Apoptosis
    -0.70
     Iwan
    -0.67
     towing
    -0.66
    UserDto
    -0.65
    رأة
    -0.65
    addUser
    -0.65
    asanjo
    -0.65
    POSITIVE LOGITS
     authentic
    5.38
     authenticity
    5.19
    authentic
    4.84
     authenticate
    4.75
     Authentic
    4.72
     authentication
    4.72
    Authentic
    4.38
     authenticated
    4.19
     Authenticity
    4.06
    authenticate
    3.84
    Activations Density 0.143%

    No Known Activations