© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70986
    Prev
    Next
    INDEX
    Explanations

    useState, AM PM, Aww, present

    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
    
    -2.55
     tepi
    -2.48
    
    -2.44
    fficking
    -2.38
    Ꮌ
    -2.36
    इटम
    -2.34
     این
    -2.31
     特写
    -2.28
    
    -2.22
    遹
    -2.22
    POSITIVE LOGITS
    ↵↵
    3.39
    (
    2.48
    <td>
    2.22
    </strong>
    2.09
     mindless
    2.06
     –
    2.05
    </em>
    1.98
    ᛬
    1.96
    ти
    1.96
    }{
    1.95
    Activations Density 0.001%

    No Known Activations