© 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. 7978
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

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

    The neuron strongly activates on lines with deep indentation (long runs of leading spaces or tabs).

    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
     ]}
    -1.00
     szint
    -0.95
     elementy
    -0.92
     näky
    -0.92
    にほんブログ村
    -0.91
    𝕬
    -0.91
     Registro
    -0.88
    oslav
    -0.86
     depuis
    -0.86
    founded
    -0.86
    POSITIVE LOGITS
    berger
    0.85
     asterisk
    0.83
     subsequently
    0.83
     później
    0.81
     later
    0.81
     barium
    0.81
     später
    0.79
    A
    0.79
     ricks
    0.79
    Scorecard
    0.77
    Activations Density 0.021%

    No Known Activations