© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67134
    Prev
    Next
    INDEX
    Explanations

    revert to previous state

    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
     renovación
    -0.98
    thest
    -0.93
     személy
    -0.93
     Necro
    -0.91
     rezept
    -0.91
    经常
    -0.91
    उत्तर
    -0.90
    셨
    -0.89
    ᓇ
    -0.88
     ninh
    -0.88
    POSITIVE LOGITS
    に戻
    1.60
     обратно
    1.50
     revert
    1.45
     reverted
    1.44
     tilbake
    1.41
     reverting
    1.33
    revert
    1.32
     return
    1.31
     back
    1.23
    goBack
    1.23
    Activations Density 0.041%

    No Known Activations