© 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. 34-GEMMASCOPE-RES-131K
    4. 109363
    Prev
    Next
    INDEX
    Explanations

    using System.Linq;

    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_34/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
     only
    -1.20
    Ạ
    -1.17
     any
    -1.14
     virtudes
    -1.05
     at
    -1.05
     more
    -1.04
    ๔
    -1.02
     large
    -0.98
    haviours
    -0.98
    ɣ
    -0.97
    POSITIVE LOGITS
    Linq
    1.21
    Tils
    1.00
    Ofic
    0.95
    などを
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
     :.
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
    などの
    0.90
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.90
    Activations Density 0.002%

    No Known Activations