© 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. 25357
    Prev
    Next
    INDEX
    Explanations

    each time

    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
     you
    -1.58
     may
    -1.27
     if
    -1.24
     it
    -1.20
     can
    -1.20
     in
    -1.18
     this
    -1.17
     now
    -1.13
     should
    -1.06
     for
    -1.03
    POSITIVE LOGITS
     jeweils
    2.42
     each
    2.22
    每次
    2.13
     fiecare
    2.06
     chaque
    2.00
    each
    1.88
     jeweiligen
    1.74
    EACH
    1.70
     каждый
    1.63
    毎回
    1.63
    Activations Density 0.056%

    No Known Activations