© 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. 22-GEMMASCOPE-RES-131K
    7. 64661
    Prev
    Next
    INDEX
    Explanations

    how to do it

    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_22/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
    -1.09
    -1.06
    -1.04
     chrétien
    -1.02
    brada
    -1.02
     mélang
    -1.02
    -1.02
     saumon
    -1.02
    toare
    -1.01
    ίο
    -1.00
    POSITIVE LOGITS
    それを
    1.38
     then
    1.24
     also
    1.23
    そして
    1.09
     therefore
    1.05
    これを
    0.94
     selben
    0.91
    だからこそ
    0.91
     vraie
    0.90
     now
    0.88
    Activations Density 0.010%

    No Known Activations