© 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. 106577
    Prev
    Next
    INDEX
    Explanations

    particular, threats, importantly, succeed

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

    subtle way, recurring payments, sensitive histories

    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
    不斷
    0.49
    大學
    0.46
    継続
    0.45
    舊
    0.45
    ्रीट
    0.45
    ܠ
    0.44
    ეგ
    0.43
     regres
    0.43
    ቃት
    0.43
    ዜ
    0.43
    POSITIVE LOGITS
    0
    0.49
     RMB
    0.48
    splitter
    0.47
    s
    0.47
    savvy
    0.44
    howto
    0.43
     frowned
    0.42
    holder
    0.41
    proxy
    0.41
    election
    0.41
    Activations Density 0.000%

    No Known Activations