© 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. 34-GEMMASCOPE-RES-131K
    7. 107214
    Prev
    Next
    INDEX
    Explanations

    copyright, developer, or specific entities

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

    The neuron fires on “namespace” or “package” name segments—i.e. the individual identifier tokens you see in URLs or import paths (for example the “developer” segment in Microsoft’s XML namespace or the “Minecraft” segment in a Java package).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     With
    -0.90
     show
    -0.86
     colloquial
    -0.81
     under
    -0.80
     continue
    -0.79
    пти
    -0.77
    ワイド
    -0.75
     remain
    -0.75
    spesies
    -0.75
    agami
    -0.74
    POSITIVE LOGITS
    AspNetCore
    0.91
    Imported
    0.90
    Ꮠ
    0.89
     ($(
    0.88
    ᷇
    0.87
    了下来
    0.84
    TEN
    0.83
     {};
    0.82
    possible
    0.82
     intit
    0.82
    Activations Density 0.000%

    No Known Activations