© 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. 85378
    Prev
    Next
    INDEX
    Explanations

    states or qualities

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

    This neuron fires on technical or academic–style prose, e.g. code‐oriented language or formal research-paper text.

    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
    こない
    -1.98
     Scritto
    -1.98
     baumwolle
    -1.92
     ſont
    -1.80
    diese
    -1.80
     pittores
    -1.77
     jezt
    -1.73
     zoude
    -1.73
     camiset
    -1.70
    ㍉
    -1.69
    POSITIVE LOGITS
     to
    2.06
     has
    1.84
     may
    1.84
     first
    1.80
     will
    1.73
     always
    1.66
     gdyż
    1.64
     is
    1.59
     In
    1.59
     before
    1.59
    Activations Density 24.138%

    No Known Activations