© 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. 22-GEMMASCOPE-RES-131K
    7. 68974
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
     from
    -2.63
    ⼥
    -2.09
     xícara
    -2.09
    ྅
    -1.99
     blatantly
    -1.99
    เกง
    -1.98
     谁
    -1.97
    ﺅ
    -1.96
     because
    -1.94
     شیپور
    -1.92
    POSITIVE LOGITS
     acclaimed
    2.41
     MOST
    2.41
     Increases
    2.36
    IBLIO
    2.31
     NEW
    2.25
     momentous
    2.23
    更に
    2.22
    珵
    2.16
     一
    2.13
    ين
    2.11
    Activations Density 0.002%

    No Known Activations