© 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. 22-GEMMASCOPE-RES-131K
    7. 95669
    Prev
    Next
    INDEX
    Explanations

    aims at/to, relates to

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

    The neuron activates on expressions stating a study’s objective or purpose (e.g. “aims to,” “is aimed at,” “investigating,” 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_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
     their
    -1.31
     themselves
    -1.13
     aqueles
    -1.07
     swojego
    -1.06
    äns
    -1.06
     jejich
    -1.05
    şekkür
    -1.04
     mercancías
    -1.02
    たびに
    -1.02
     उनकी
    -1.01
    POSITIVE LOGITS
     also
    1.35
     only
    1.35
     TAMBÉM
    1.27
     two
    1.23
    4
    1.14
    เพียง
    1.02
    //
    1.00
    兩種
    1.00
    2
    1.00
    3
    1.00
    Activations Density 0.187%

    No Known Activations