© 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. 73846
    Prev
    Next
    INDEX
    Explanations

    offsetting and balancing

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

    The neuron activates on occurrences of the string “offset” (including “offsetting” and other inflections).

    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
    .
    -3.38
    of
    -2.13
    в
    -2.02
    de
    -1.93
     Here
    -1.91
    </b>
    -1.85
    禤
    -1.83
    section
    -1.80
     During
    -1.80
    out
    -1.79
    POSITIVE LOGITS
    𓐍
    2.34
    ︲
    2.08
    のほうが
    2.06
    特に
    2.00
    ſelf
    1.98
    ೢ
    1.95
     ſta
    1.91
    謖
    1.89
    ⬮
    1.87
    Ꮴ
    1.85
    Activations Density 0.007%

    No Known Activations