© 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. 22-GEMMASCOPE-RES-131K
    7. 72578
    Prev
    Next
    INDEX
    Explanations

    initializer patterns

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

    The neuron triggers on programming API type names (e.g. Context, AttributeSet, Serial, coder).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    様に
    -1.10
    复制代码
    -1.09
    chê
    -1.09
    VILLE
    -1.05
    、「
    -1.04
    防疫
    -1.02
    providedIn
    -0.99
     оча
    -0.97
    your
    -0.97
    графі
    -0.94
    POSITIVE LOGITS
     herido
    1.22
    いたしました
    1.22
    がありますが
    1.20
     xix
    1.12
    させていただきました
    1.11
    .¹
    1.08
    請繼續
    1.05
    Équipe
    1.05
    立場
    1.05
    结束后
    1.03
    Activations Density 0.000%

    No Known Activations