© 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. 22-GEMMASCOPE-RES-131K
    7. 66011
    Prev
    Next
    INDEX
    Explanations

    new or again

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

    The neuron is a high‐level “content word” detector—it fires strongly on meaningful lexical items (verbs, nouns, adjectives, numbers) and stays off for common function words and punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     первого
    -1.03
     ersten
    -1.02
     erste
    -1.01
     первых
    -0.99
     первые
    -0.98
     первом
    -0.92
     первый
    -0.90
     eerste
    -0.90
    elesaikan
    -0.90
    ズム
    -0.89
    POSITIVE LOGITS
     again
    2.30
     new
    2.09
     جدید
    2.06
     очеред
    2.02
    again
    1.87
    新的
    1.79
     AGAIN
    1.73
     جديد
    1.70
     nuevo
    1.66
     nuovamente
    1.63
    Activations Density 0.143%

    No Known Activations