© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93483
    Prev
    Next
    INDEX
    Explanations

    reporting speech or thoughts

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

    The neuron strongly fires on the final subtoken of capitalized proper names (especially surnames).

    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
     Note
    -1.26
     NOTE
    -1.16
    Note
    -1.16
     nota
    -1.09
    note
    -1.08
    bum
    -1.05
     note
    -1.03
     gotten
    -1.02
    noted
    -1.01
     еще
    -0.99
    POSITIVE LOGITS
     said
    1.69
     believes
    1.40
     believe
    1.28
     reck
    1.12
     today
    1.11
     yesterday
    1.08
     revealed
    1.02
     believed
    1.00
     felt
    0.99
     believing
    0.93
    Activations Density 0.037%

    No Known Activations