© 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. 99172
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and determiners

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

    The neuron flags terms having to do with personal‐data rights, consent, and related legal/permission language (e.g. “your,” “privacy,” “permission,” “security”).

    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
     père
    -1.59
     WITHIN
    -1.16
     requiere
    -1.14
     dette
    -1.13
    needed
    -1.13
     rivales
    -1.12
     clásicos
    -1.12
     nô
    -1.11
     собы
    -1.09
    laria
    -1.08
    POSITIVE LOGITS
     their
    2.19
     those
    1.86
     his
    1.86
     your
    1.77
     our
    1.74
     its
    1.66
     ability
    1.61
     what
    1.56
     own
    1.56
     that
    1.48
    Activations Density 0.089%

    No Known Activations