© 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. 10-GEMMASCOPE-RES-131K
    7. 104770
    Prev
    Next
    INDEX
    Explanations

    all i do is

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

    The neuron fires on second-person instructional constructions—especially the “all you have to do is …” style of giving directions.

    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
     herhangi
    -2.13
    </td>
    -1.91
    ↵↵
    -1.90
     definitivamente
    -1.77
     realmente
    -1.73
     любом
    -1.67
    BUT
    -1.63
     totalmente
    -1.62
     \
    -1.60
    嚎
    -1.59
    POSITIVE LOGITS
     some
    2.44
     their
    2.36
    Ꮔ
    1.98
     the
    1.92
     gets
    1.87
     a
    1.78
    мання
    1.78
    ientos
    1.73
    卨
    1.71
     this
    1.68
    Activations Density 0.006%

    No Known Activations