© 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. 102811
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

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

    The neuron fires strongly on the leading segment (and hyphen) of hyphenated or reduplicative compound expressions (e.g. fast-track, high-sticking, naysayer, poo-poo, sugarcoat, short-circuit).

    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
     podríamos
    -0.84
    ╹
    -0.79
     drones
    -0.79
     tendrás
    -0.78
    URRED
    -0.77
    اكل
    -0.77
     nena
    -0.76
    ન્
    -0.76
    picious
    -0.76
    Quand
    -0.75
    POSITIVE LOGITS
     basing
    0.91
    lining
    0.80
    ITIS
    0.80
     य
    0.77
    sitis
    0.73
     reigned
    0.73
     Mere
    0.72
    ball
    0.72
     compatibles
    0.70
     हो
    0.69
    Activations Density 0.066%

    No Known Activations