© 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. 21463
    Prev
    Next
    INDEX
    Explanations

    predicted outcomes

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

    The neuron fires specifically on the word “predicted,” especially where it introduces a numerical or model‐derived value.

    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
     или
    -2.88
    ꜆
    -2.81
    or
    -2.70
     PUSTAKA
    -2.63
    ńskich
    -2.61
     یا
    -2.50
     atau
    -2.50
    或
    -2.47
    and
    -2.45
    私は
    -2.44
    POSITIVE LOGITS
    媗
    2.63
    稣
    2.59
    鰾
    2.50
    抔
    2.47
    とも言
    2.41
    逖
    2.41
    でございます
    2.39
     Their
    2.38
    姈
    2.36
    ஂ
    2.34
    Activations Density 0.005%

    No Known Activations