© 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. 10-GEMMASCOPE-RES-131K
    4. 104978
    Prev
    Next
    INDEX
    Explanations

    introduces a clause

    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_10/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
     the
    -2.19
    Ostat
    -2.06
    えっ
    -2.06
    Podob
    -2.05
    Obec
    -2.05
    こだ
    -2.03
     innych
    -2.00
    サード
    -1.92
     kontaktu
    -1.91
    Počet
    -1.91
    POSITIVE LOGITS
    。「
    2.06
    x
    1.91
    ؛
    1.87
     when
    1.87
     was
    1.82
    尤其
    1.79
    💜
    1.77
     during
    1.74
     they
    1.74
    s
    1.73
    Activations Density 0.049%

    No Known Activations