© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48761
    Prev
    Next
    INDEX
    Explanations

    actions directed at her

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

    The neuron strongly activates on dynamic action verbs that move a narrative forward.

    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
    He
    -2.23
     esso
    -1.88
    They
    -1.80
     они
    -1.68
     оно
    -1.58
     éste
    -1.55
     dessen
    -1.37
     éstos
    -1.31
    they
    -1.31
    彼らの
    -1.28
    POSITIVE LOGITS
     she
    6.47
     her
    5.94
    她
    3.86
     ей
    3.59
     она
    3.53
     ją
    3.48
    เธอ
    3.33
     ее
    3.30
     её
    3.11
     nią
    3.09
    Activations Density 0.071%

    No Known Activations