© 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. 6884
    Prev
    Next
    INDEX
    Explanations

    phrase beginnings

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

    The neuron strongly activates on the very first (often longer, heading-style) word at the start of each text block.

    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
     essencial
    -1.80
     palmas
    -1.72
     involunt
    -1.68
     uvas
    -1.67
     farol
    -1.59
     agricultura
    -1.57
     sopa
    -1.53
     salada
    -1.52
     cortado
    -1.52
     pione
    -1.52
    POSITIVE LOGITS
     –
    1.45
    ;
    1.33
     também
    1.23
     berücksich
    1.18
    ,
    1.15
     =
    1.14
    );
    1.14
    .”
    1.13
    "
    1.10
    )
    1.09
    Activations Density 0.318%

    No Known Activations