© 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. 10-GEMMASCOPE-RES-131K
    7. 65854
    Prev
    Next
    INDEX
    Explanations

    him, her, his, it, them

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

    The neuron fires on transitive verbs—i.e. action words that take a direct object.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.88
    6
    -1.53
    5
    -1.52
    2
    -1.50
     
    -1.41
    1
    -1.21
    "
    -1.20
    7
    -1.19
     the
    -1.19
    as
    -1.19
    POSITIVE LOGITS
    禩
    1.61
     nevo
    1.45
     poliuret
    1.42
     egip
    1.41
    眛
    1.34
     décé
    1.32
     jugo
    1.31
     aéri
    1.30
     dites
    1.27
     Matos
    1.27
    Activations Density 0.037%

    No Known Activations