© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66735
    Prev
    Next
    INDEX
    Explanations

    completion and its aftermath

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

    The neuron activates on occurrences of the word “end” (especially “ended”), flagging mentions of something coming to a conclusion.

    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
     to
    -2.02
     of
    -1.82
     /
    -1.68
     desde
    -1.64
     através
    -1.59
    allenge
    -1.47
    ’,
    -1.45
    InputBorder
    -1.43
     sejak
    -1.43
    ції
    -1.41
    POSITIVE LOGITS
     embalaje
    1.66
    非常好
    1.63
     decoracion
    1.58
     secado
    1.58
     maleta
    1.58
    prende
    1.56
     repuesto
    1.55
     abiye
    1.51
     bebés
    1.48
     Excessive
    1.48
    Activations Density 0.031%

    No Known Activations