© 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. 36633
    Prev
    Next
    INDEX
    Explanations

    numbers and decimal point format

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     хви
    -0.88
     uzupeł
    -0.88
    걍
    -0.87
    ־ה
    -0.86
     buvo
    -0.86
    姪
    -0.82
    phants
    -0.81
     тільки
    -0.79
    じゃなくて
    -0.79
    ケ
    -0.79
    POSITIVE LOGITS
     schreef
    0.91
     cramped
    0.90
    ]^{-
    0.85
    fdata
    0.85
    loggen
    0.84
    钍
    0.84
     energe
    0.83
     veda
    0.83
    耗
    0.83
     sánh
    0.82
    Activations Density 0.083%

    No Known Activations