© 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. 71194
    Prev
    Next
    INDEX
    Explanations

    otter, ANC, foothills

    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
    ༀ
    -3.84
    乆
    -3.25
    臜
    -3.19
    蚰
    -3.02
    神
    -2.97
    䛗
    -2.91
    𔘓
    -2.89
    ᕱ
    -2.80
    荩
    -2.80
    偁
    -2.78
    POSITIVE LOGITS
    {
    3.19
     Our
    3.16
     There
    3.08
    I
    2.86
    .,
    2.73
     Although
    2.73
     Hinblick
    2.66
     Contrary
    2.64
    ),
    2.61
     However
    2.59
    Activations Density 0.007%

    No Known Activations