© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29764
    Prev
    Next
    INDEX
    Explanations

    aid or donations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eness
    0.40
    cheidet
    0.39
     obraz
    0.39
     necessitate
    0.38
     пробе
    0.38
    isać
    0.38
    ዐ
    0.38
     educate
    0.37
    pawns
    0.37
    아
    0.37
    POSITIVE LOGITS
     donations
    1.05
     donating
    0.94
     donation
    0.89
     donated
    0.88
     funding
    0.87
    捐
    0.86
     gifts
    0.85
     donate
    0.84
     generous
    0.80
     generosity
    0.80
    Activations Density 0.095%

    No Known Activations