© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 530
    Prev
    Next
    INDEX
    Explanations

    Humanitarian aid, charities, hotlines

    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_16_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
     राज
    0.45
    p
    0.43
     वही
    0.41
    ther
    0.40
    ل
    0.38
    त्ति
    0.37
    ö
    0.37
     determining
    0.36
     sprinting
    0.36
    ตาม
    0.36
    POSITIVE LOGITS
    י
    0.63
     Charities
    0.59
     karit
    0.58
     charities
    0.56
    čili
    0.55
    نې
    0.55
    公益
    0.53
    ي
    0.51
    ()]
    0.50
    مني
    0.50
    Activations Density 0.630%

    No Known Activations