© 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. 111213
    Prev
    Next
    INDEX
    Explanations

    subject to the

    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
    </h1>
    -1.47
    』、
    -1.46
     "
    -1.38
     and
    -1.37
     natomiast
    -1.28
    }$,
    -1.27
     například
    -1.26
    ...
    -1.25
    n
    -1.23
     
    -1.20
    POSITIVE LOGITS
    kredit
    1.47
     zima
    1.45
     diferentes
    1.41
    siębior
    1.41
    ĭ
    1.36
    荇
    1.35
    Identyfik
    1.35
    (!__
    1.34
    MITTED
    1.34
     élégante
    1.34
    Activations Density 0.014%

    No Known Activations