© 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. 10-GEMMASCOPE-RES-131K
    7. 41872
    Prev
    Next
    INDEX
    Explanations

    in Tamil

    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
     for
    -1.77
     about
    -1.74
     to
    -1.45
     such
    -1.35
    一个小
    -1.31
     then
    -1.30
    )
    -1.24
    伱
    -1.23
    then
    -1.23
    -
    -1.19
    POSITIVE LOGITS
     llenos
    1.35
     spodnie
    1.33
    }$.\\
    1.32
    ("__
    1.27
    yoruz
    1.26
    iK
    1.24
    AuthGuard
    1.23
    ቷ
    1.22
     strán
    1.22
     露天
    1.20
    Activations Density 0.150%

    No Known Activations