© 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. 10-GEMMASCOPE-RES-131K
    7. 67314
    Prev
    Next
    INDEX
    Explanations

    love you more

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

    The neuron strongly activates on occurrences of the phrase “love you” (including variants like “I love you,” “loves you,” etc.).

    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
     our
    -1.71
    諴
    -1.66
     Makes
    -1.59
     identitas
    -1.55
    Why
    -1.53
    ientos
    -1.52
    　　-
    -1.51
    淥
    -1.50
    Using
    -1.49
    about
    -1.46
    POSITIVE LOGITS
    cún
    1.68
    呖
    1.59
    }
    1.57
    "
    1.50
     تمامی
    1.46
     quieren
    1.41
    ]
    1.41
    >
    1.36
     they
    1.34
     admiten
    1.34
    Activations Density 0.010%

    No Known Activations