© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129129
    Prev
    Next
    INDEX
    Explanations

    human dignity, dexterity

    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
    扨
    -2.84
    ll
    -2.77
     –
    -2.48
    に
    -2.47
     Mitgliedern
    -2.47
    哢
    -2.28
    訁
    -2.23
                    
    -2.17
    偸
    -2.11
     They
    -2.08
    POSITIVE LOGITS
    蔟
    2.05
    ⫹
    2.00
    泱
    1.99
    釓
    1.99
     blurred
    1.98
    ¹)
    1.94
     zincir
    1.93
    ’
    1.92
    strator
    1.90
    琑
    1.88
    Activations Density 0.001%

    No Known Activations