© 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. 12295
    Prev
    Next
    INDEX
    Explanations

    shooting

    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
    {
    -1.72
    2
    -1.65
    }
    -1.63
     после
    -1.55
    after
    -1.48
    7
    -1.43
    超過
    -1.42
    aikan
    -1.38
    还有
    -1.37
    “
    -1.37
    POSITIVE LOGITS
    柺
    1.59
    穑
    1.59
    霂
    1.51
    퐼
    1.50
    芫
    1.49
    渽
    1.48
     ventilación
    1.45
     éte
    1.45
     Inſ
    1.44
    idends
    1.43
    Activations Density 0.014%

    No Known Activations