© 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. 67196
    Prev
    Next
    INDEX
    Explanations

    lists of names

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

    This neuron activates on front‐matter metadata tokens—author names, numeric identifiers (like section or version numbers), and similar header/title elements.

    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
     않습니다
    -0.98
     GetEnumerator
    -0.95
    cstr
    -0.95
    ないけど
    -0.92
     tonel
    -0.91
    Características
    -0.90
    createView
    -0.88
    moderne
    -0.88
     tambor
    -0.87
     творо
    -0.87
    POSITIVE LOGITS
     student
    1.09
    apping
    1.07
    java
    1.06
    name
    1.02
     github
    1.00
    čnega
    1.00
     trastorno
    1.00
    Name
    0.99
    input
    0.94
     java
    0.94
    Activations Density 0.023%

    No Known Activations