© 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. 102654
    Prev
    Next
    INDEX
    Explanations

    left to right

    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
    {
    -2.28
    逐渐
    -1.77
    y
    -1.77
    渐渐
    -1.73
     obyvateľov
    -1.73
    b
    -1.73
    ),
    -1.67
    ↵↵
    -1.64
    之类的
    -1.63
    专门
    -1.59
    POSITIVE LOGITS
     of
    1.87
     a
    1.84
     homicidio
    1.66
    ées
    1.66
    kyat
    1.60
     健
    1.60
    畦
    1.55
    We
    1.53
     márm
    1.52
     asesinato
    1.51
    Activations Density 0.010%

    No Known Activations