© 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. 38712
    Prev
    Next
    INDEX
    Explanations

    SPECIAL roles or designations

    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
    
    -2.92
    𓁹
    -2.77
     asesor
    -2.63
    𝗟
    -2.59
    亹
    -2.58
     perfekte
    -2.50
    撳
    -2.47
     icône
    -2.45
     desblo
    -2.44
    秕
    -2.44
    POSITIVE LOGITS
    a
    5.03
    3
    4.44
    6
    4.38
    7
    4.19
    ”
    3.98
    2
    3.81
    8
    3.77
    4
    3.67
    What
    3.47
    1
    3.31
    Activations Density 0.029%

    No Known Activations