© 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. 127267
    Prev
    Next
    INDEX
    Explanations

    daughter, sisters, blue

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

    The neuron fires most strongly on kinship or family‐relationship words (e.g. son, daughter, sister).

    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
    НИЙ
    -1.28
    herin
    -1.23
    tility
    -1.19
    miri
    -1.18
    érales
    -1.16
    TokenNameRPAREN
    -1.16
     câbles
    -1.14
    ⩾
    -1.14
    ční
    -1.13
    phanie
    -1.13
    POSITIVE LOGITS
     much
    1.30
    .
    1.16
     each
    1.10
     Verbesserung
    1.09
     Each
    1.09
    ا
    1.06
     called
    1.05
     буду
    1.05
    ه
    1.03
     its
    1.02
    Activations Density 0.018%

    No Known Activations