© 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. 112638
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron activates on occurrences of the character sequence “noi” within words.

    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
    饪
    -2.61
    J
    -2.44
     gustaba
    -2.30
     greateſt
    -2.28
    F
    -2.23
    可以
    -2.22
    igkeiten
    -2.22
     هایی
    -2.20
    的一个
    -2.20
    },
    -2.19
    POSITIVE LOGITS
     comprised
    2.63
    en
    2.48
    thig
    2.45
    品牌的
    2.44
    蓠
    2.39
     spezielle
    2.36
    他们在
    2.33
     penchant
    2.30
    饜
    2.27
     are
    2.20
    Activations Density 0.000%

    No Known Activations