© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34749
    Prev
    Next
    INDEX
    Explanations

    quality and value

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

    The neuron fires on marketing‐style terms that describe positive product or service attributes (e.g. quality, effectiveness, safety, value, service).

    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
     valleys
    -0.88
     quotation
    -0.87
     quartz
    -0.85
    ők
    -0.83
    Graf
    -0.82
     wachs
    -0.82
    alquiler
    -0.81
    Trọng
    -0.81
    torque
    -0.79
    Ries
    -0.78
    POSITIVE LOGITS
     quantity
    1.05
     price
    0.86
     standards
    0.85
     assurance
    0.84
     consistency
    0.82
     Quantity
    0.82
    Hdr
    0.81
    REWRITE
    0.80
     jasa
    0.80
    quantity
    0.79
    Activations Density 0.044%

    No Known Activations