© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79785
    Prev
    Next
    INDEX
    Explanations

    prefixes to names

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

    This neuron detects user “nicknames” or handles (speaker names) in chat/forum logs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    usernames or handles in chat logs and online forums.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     in
    -1.52
     on
    -1.51
     Başkanı
    -1.31
    struts
    -1.27
     with
    -1.25
    edith
    -1.22
    🦠
    -1.20
     måste
    -1.20
     at
    -1.18
     sido
    -1.16
    POSITIVE LOGITS
    u
    1.31
     entraîner
    1.29
    g
    1.25
    mathrm
    1.23
    あー
    1.20
    	
    1.20
    ou
    1.15
    						
    1.15
    rightarrow
    1.14
    n
    1.14
    Activations Density 0.011%

    No Known Activations