© 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. 112621
    Prev
    Next
    INDEX
    Explanations

    body parts and accessories

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

    The neuron fires on concrete object nouns (side, hand, air, belt, board) often appearing in prepositional/idiomatic phrases.

    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
     there
    -1.36
     considerada
    -1.32
    疍
    -1.27
    zsh
    -1.27
     on
    -1.25
     usamos
    -1.24
     verbess
    -1.24
     contado
    -1.21
     out
    -1.19
     beeindruck
    -1.18
    POSITIVE LOGITS
    媖
    1.47
    llavero
    1.38
    ッサン
    1.38
    𖣘
    1.36
    ન
    1.30
     Comissão
    1.27
    Pengertian
    1.27
    夘
    1.26
    
    1.24
     чего
    1.23
    Activations Density 0.044%

    No Known Activations