© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69180
    Prev
    Next
    INDEX
    Explanations

    my followed by code identifiers

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

    This neuron activates on the first-person possessive pronoun “my.”

    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
    があるので
    -1.79
    は
    -1.76
    struzioni
    -1.66
    greja
    -1.64
    なので
    -1.62
    を
    -1.61
    が
    -1.52
    などの
    -1.52
    <bos>
    -1.52
    を持つ
    -1.51
    POSITIVE LOGITS
     new
    1.73
    It
    1.63
    _
    1.62
    N
    1.59
    providedIn
    1.59
    new
    1.53
    j
    1.52
    場所で
    1.50
    購入した
    1.48
    D
    1.47
    Activations Density 0.032%

    No Known Activations