© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66421
    Prev
    Next
    INDEX
    Explanations

    new introduction johnny method

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

    The neuron fires on template‐language control delimiters (e.g. the “{%” … “%}” tags) used in things like Jinja/Liquid/other templating code.

    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
    dekat
    -1.04
    عال
    -1.02
     by
    -1.01
    lampa
    -0.96
     baratas
    -0.95
     burbu
    -0.94
     giving
    -0.93
     смесь
    -0.93
     taking
    -0.91
     every
    -0.90
    POSITIVE LOGITS
    ne
    1.10
    na
    1.08
    till
    1.07
     alcune
    1.05
    ‑
    1.04
    bre
    1.02
    bi
    1.02
    ata
    1.01
    ru
    1.00
    ill
    1.00
    Activations Density 0.000%

    No Known Activations