© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    in its various forms

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

    This neuron detects the possessive pronoun “its” when it introduces a list or enumeration of aspects (e.g. “its three dimensions,” “in all its forms/variety/diversity”).

    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
     into
    -1.02
     about
    -0.94
    peł
    -0.92
    情報は
    -0.91
     Informações
    -0.90
     etc
    -0.90
     contribute
    -0.90
     on
    -0.90
     obce
    -0.88
    パーティー
    -0.88
    POSITIVE LOGITS
     its
    1.34
    Ingredientes
    1.05
    UNIVERSIDAD
    1.04
     melk
    1.02
    €“
    0.98
    кает
    0.98
    "@
    0.98
    mysqli
    0.97
     borracha
    0.97
    sturm
    0.95
    Activations Density 0.031%

    No Known Activations