© 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. 48108
    Prev
    Next
    INDEX
    Explanations

    Spearhead, Spearman correlation

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

    The neuron is keyed to the letter sequence “spear,” strongly activating on any token containing that substring.

    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
    𖤍
    -2.75
    𖣔
    -2.59
    ☫
    -2.56
     &
    -2.45
     amitié
    -2.42
     brutal
    -2.33
    !"
    -2.25
     です
    -2.20
     evade
    -2.19
    荟
    -2.19
    POSITIVE LOGITS
    iritto
    2.64
    <bos>
    2.52
     öffnungszeiten
    2.41
    驁
    2.33
    viembre
    2.31
     zeitung
    2.30
     hial
    2.30
     constituting
    2.27
     oogen
    2.27
     ナビ
    2.19
    Activations Density 0.004%

    No Known Activations