© 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. 22-GEMMASCOPE-RES-131K
    7. 25743
    Prev
    Next
    INDEX
    Explanations

    mañana de la mañana

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

    The neuron is effectively inactive (“dead”) and does not reliably respond to any particular tokens.

    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
    淠
    -1.36
     miniaturka
    -1.28
     xadrez
    -1.23
     Produtos
    -1.23
     gewi
    -1.23
    𓆏
    -1.21
     zoude
    -1.21
     artesanato
    -1.20
    蚰
    -1.20
     Heilige
    -1.20
    POSITIVE LOGITS
     this
    1.66
     when
    1.60
     some
    1.38
     any
    1.31
     because
    1.27
     at
    1.24
     these
    1.21
     their
    1.20
     an
    1.16
     with
    1.10
    Activations Density 0.024%

    No Known Activations