© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40481
    Prev
    Next
    INDEX
    Explanations

    round robin, FIFO, DRAM

    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
    咴
    -2.45
     \
    -2.44
    甚至
    -2.41
    
    -2.39
     родителей
    -2.38
     ältere
    -2.36
    ⧠
    -2.30
     unangemessene
    -2.20
     klassische
    -2.20
    en
    -2.17
    POSITIVE LOGITS
    u
    2.33
    </strong>
    2.11
    </h3>
    2.00
    replyreport
    1.98
    ()),
    1.98
    」
    1.95
    🌹
    1.89
     télécharge
    1.86
    }:
    1.85
    </sub>
    1.84
    Activations Density 0.003%

    No Known Activations