© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43092
    Prev
    Next
    INDEX
    Explanations

    mimicry and imitation

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

    The neuron reliably detects occurrences of the root “mimic” (including “mimic,” “mimicry,” and related morphological variants).

    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
     \
    -3.84
    ↵↵
    -2.86
     más
    -2.53
    )
    -2.22
     '';
    -2.16
     name
    -2.08
    ت
    -2.08
    на
    -2.06
     fortsetter
    -2.05
    撓
    -2.05
    POSITIVE LOGITS
    y
    3.42
    ୩
    2.64
    寕
    2.47
    蹀
    2.31
     脸
    2.28
     offrent
    2.27
    wieś
    2.25
    Kenapa
    2.23
     亲
    2.23
    Hanya
    2.20
    Activations Density 0.003%

    No Known Activations