© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127794
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities

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

    The neuron specializes in spotting capitalized proper nouns and technical acronyms (named entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     certaines
    -1.36
     många
    -1.23
     Monaten
    -1.15
     uzman
    -1.14
    Galería
    -1.13
     quelquefois
    -1.13
     avocat
    -1.12
     doucement
    -1.10
     niektor
    -1.09
     花纹
    -1.09
    POSITIVE LOGITS
     it
    2.41
     as
    1.75
     its
    1.73
     another
    1.39
     to
    1.34
     in
    1.33
     seems
    1.31
     there
    1.30
     (
    1.29
     so
    1.23
    Activations Density 0.492%

    No Known Activations