© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6360
    Prev
    Next
    INDEX
    Explanations

    Im- followed by word parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    alanine
    0.58
     ပ
    0.57
    ół
    0.56
    pexels
    0.56
     Следу
    0.56
    whole
    0.55
    wide
    0.55
     অবস্থ
    0.54
     ట
    0.54
    ify
    0.54
    POSITIVE LOGITS
     Imp
    1.08
     Im
    1.02
     IMP
    0.99
     imp
    0.97
     impe
    0.93
    Im
    0.87
     इंप
    0.80
     imping
    0.79
     impost
    0.79
     impeachment
    0.75
    Activations Density 0.155%

    No Known Activations