© 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. 34-GEMMASCOPE-RES-131K
    7. 108336
    Prev
    Next
    INDEX
    Explanations

    people and places

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

    The neuron fires on technical/programming jargon—especially code- or system-related terms (e.g. function, file, CreateUser, Chromium, zombie processes, etc.).

    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
    okhttp
    -1.20
     APPELLANT
    -1.16
     esportivo
    -1.06
    ∽
    -0.98
    company
    -0.96
    %;
    -0.95
    our
    -0.94
    انجليز
    -0.92
    缁
    -0.92
     PLAINTIFF
    -0.91
    POSITIVE LOGITS
    </blockquote>
    1.25
    [\
    1.20
     ...)
    1.16
     ....
    1.06
     ...]
    1.05
     would
    1.05
    OBJETIVOS
    1.05
    子が
    1.04
    子は
    1.04
    rebbe
    1.00
    Activations Density 0.070%

    No Known Activations