© 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. 34-GEMMASCOPE-RES-131K
    7. 78931
    Prev
    Next
    INDEX
    Explanations

    quickly established or become

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

    The neuron fires on phrasing that signals organizational growth or success (e.g. “has quickly grown,” “became known,” “has become”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    СТЬ
    -0.86
     maille
    -0.85
    💑
    -0.81
    Ų
    -0.81
    футбо
    -0.80
    .‏
    -0.79
    kunci
    -0.76
    ندما
    -0.76
    WireFormat
    -0.75
     jupe
    -0.75
    POSITIVE LOGITS
     become
    2.11
     establishing
    2.02
     earned
    2.02
     carved
    2.00
     establish
    1.98
     carving
    1.86
     gained
    1.86
     quickly
    1.84
     gain
    1.79
     carve
    1.77
    Activations Density 0.090%

    No Known Activations