© 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. 44411
    Prev
    Next
    INDEX
    Explanations

    with a following descriptor

    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
    𓆜
    -2.30
     terlalu
    -2.17
    噚
    -2.11
    věř
    -2.05
    
    -2.03
     ยาว
    -1.98
    Ꮗ
    -1.95
     useAppContext
    -1.94
    ).)
    -1.93
    сах
    -1.88
    POSITIVE LOGITS
     regard
    3.70
     regards
    3.09
     emphasis
    2.66
    stood
    2.56
    a
    2.41
     whom
    2.39
     hints
    2.31
    standing
    2.30
     respect
    2.27
     behulp
    2.20
    Activations Density 0.435%

    No Known Activations