© 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. 9456
    Prev
    Next
    INDEX
    Explanations

    Poké-Ball, Sun-Jun dates, ISBNs

    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
    </i>
    -1.84
     policia
    -1.45
    ktör
    -1.45
    ;
    
    -1.43
    已有
    -1.30
    MethodManager
    -1.25
     garantia
    -1.24
     вже
    -1.23
     już
    -1.23
    ')))
    -1.22
    POSITIVE LOGITS
    {
    1.53
    時は
    1.49
    ↵↵
    1.36
    </h4>
    1.27
    D
    1.22
    僥
    1.17
    讀書
    1.16
    ándor
    1.13
    是個
    1.13
     need
    1.12
    Activations Density 0.005%

    No Known Activations