© 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. 128926
    Prev
    Next
    INDEX
    Explanations

    pros and cons

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

    The neuron fires on list‐style summary headings (e.g. “Pros,” “Cons,” “Strengths”) that introduce advantage/disadvantage bullet points.

    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
     The
    -2.08
     \&
    -1.61
     "[
    -1.59
     we
    -1.47
     afecta
    -1.45
     Betrag
    -1.41
    Galería
    -1.40
     peculiarity
    -1.39
     perasaan
    -1.38
     deshalb
    -1.37
    POSITIVE LOGITS
    _
    2.06
    er
    2.02
     flèche
    1.77
    :
    1.74
     plastiques
    1.70
     للتح
    1.70
    逊
    1.66
     heet
    1.64
     gena
    1.64
     groen
    1.59
    Activations Density 0.002%

    No Known Activations