© 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. 58067
    Prev
    Next
    INDEX
    Explanations

    questions and experts

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

    This neuron fires on enthusiastic customer‐testimonial language praising a service or venue (e.g., words expressing strong positive feedback and help).

    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
     but
    -1.08
    نما
    -0.96
     konser
    -0.96
     कैसी
    -0.94
     naszych
    -0.92
    😉
    -0.91
    chriften
    -0.91
     interesante
    -0.91
     нашем
    -0.90
    😥
    -0.90
    POSITIVE LOGITS
    kyard
    1.07
     Mr
    0.98
     chaque
    0.96
     systematic
    0.95
    ismatic
    0.93
     Leute
    0.92
    ఞ
    0.90
    :✨
    0.89
     really
    0.88
     "`
    0.88
    Activations Density 0.011%

    No Known Activations