© 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. 84373
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     teşekkür
    -1.38
    ]=>
    -1.35
     Controle
    -1.30
    きは
    -1.27
    山的
    -1.24
    干脆
    -1.20
    他没有
    -1.18
    两人的
    -1.17
    辿
    -1.16
     à
    -1.16
    POSITIVE LOGITS
     endast
    1.78
    You
    1.52
     eneste
    1.50
     You
    1.48
    This
    1.45
     tentang
    1.42
    4
    1.41
     or
    1.41
     svårt
    1.30
    If
    1.29
    Activations Density 0.055%

    No Known Activations