© 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. 34-GEMMASCOPE-RES-131K
    7. 76703
    Prev
    Next
    INDEX
    Explanations

    to perform actions

    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_34/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
     helping
    -1.43
     being
    -1.34
     pomá
    -1.23
     helps
    -1.19
     helpt
    -1.13
    être
    -1.09
     کمک
    -1.05
     helped
    -1.05
     help
    -1.03
     becoming
    -1.02
    POSITIVE LOGITS
     achieve
    1.79
    Achie
    1.71
     obtain
    1.64
     achieved
    1.37
     Achieving
    1.33
     Achieve
    1.31
    achieve
    1.29
     achie
    1.28
     achieving
    1.26
     obtaining
    1.22
    Activations Density 0.371%

    No Known Activations