© 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. 39941
    Prev
    Next
    INDEX
    Explanations

    Roth IRA

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

    The neuron activates on occurrences of the substring “Roth” in names or titles.

    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
    ll
    -2.97
    ޙ
    -2.83
    er
    -2.66
    A
    -2.63
    1
    -2.56
    他们在
    -2.53
    E
    -2.53
    un
    -2.53
    你有
    -2.52
    你不
    -2.50
    POSITIVE LOGITS
    ’
    3.77
    LoS
    2.52
     ascertain
    2.48
    ৪
    2.22
     وم
    2.22
     builds
    2.20
    荐
    2.20
     By
    2.20
    玘
    2.17
    </h2>
    2.16
    Activations Density 0.016%

    No Known Activations