© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73957
    Prev
    Next
    INDEX
    Explanations

    technical definitions and components

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

    The neuron flags specialized technical jargon or domain‐specific terminology in the text.

    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
    T
    -0.92
    hi
    -0.88
    ig
    -0.85
    sier
    -0.84
    ap
    -0.84
    ファイル
    -0.84
    不太
    -0.84
     a
    -0.83
    setTimeout
    -0.83
    ar
    -0.82
    POSITIVE LOGITS
     ciclismo
    1.20
    Pengertian
    1.06
    Jawaban
    1.05
    閹
    1.01
    ඥ
    0.98
    Berat
    0.95
    CWE
    0.95
    Penjelasan
    0.94
     diskon
    0.94
     itself
    0.94
    Activations Density 0.219%

    No Known Activations