© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14700
    Prev
    Next
    INDEX
    Explanations

    tips

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     úrov
    0.56
     alm
    0.54
    捒
    0.52
     alem
    0.51
     நூற்றாண்டின்
    0.50
     Alem
    0.50
     zarządz
    0.50
     hergestellt
    0.50
     össz
    0.49
     banned
    0.48
    POSITIVE LOGITS
    Tip
    1.26
     tip
    1.19
     Tip
    1.10
    tip
    1.05
    팁
    1.04
    TIP
    1.00
     tipped
    0.96
    Tips
    0.93
     tipping
    0.92
    tips
    0.88
    Activations Density 0.000%

    No Known Activations