© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32900
    Prev
    Next
    INDEX
    Explanations

    Afghanistan directed

    np_acts-logits-general · gemini-2.5-flash-lite

    seeking help and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vaping
    0.37
     (
    0.35
     our
    0.35
     Version
    0.35
     this
    0.34
     fueled
    0.33
     Fortnite
    0.33
     herein
    0.33
     Venue
    0.32
     Blockchain
    0.32
    POSITIVE LOGITS
    ヨーロッパ
    0.38
    他們
    0.36
    ૄ
    0.36
    They
    0.36
     آنها
    0.35
    उन्होंने
    0.34
    ckså
    0.34
    Democrats
    0.34
     खूबस
    0.33
    𝔀
    0.33
    Activations Density 0.048%

    No Known Activations