© 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. 21118
    Prev
    Next
    INDEX
    Explanations

    ebook fanfic download availability

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

    The neuron selectively responds to uncommon, domain-specific jargon terms (e.g. programming class names, acronyms, ebook/fanfic labels, technical descriptors).

    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
    蘩
    -2.66
    龊
    -2.64
    
    -2.56
     batal
    -2.56
    書類
    -2.52
    这让
    -2.45
    闞
    -2.45
     书法
    -2.45
     anún
    -2.44
    ᯾
    -2.42
    POSITIVE LOGITS
    k
    4.53
    f
    3.84
    p
    3.70
    m
    3.58
    ca
    3.45
    z
    3.39
    c
    3.39
    e
    3.36
    u
    3.31
    os
    3.30
    Activations Density 0.016%

    No Known Activations