© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16291
    Prev
    Next
    INDEX
    Explanations

    foreign words for almost

    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
     insanity
    0.64
     madness
    0.57
     모습
    0.57
     nightmare
    0.56
     ভয়ানক
    0.56
    其
    0.56
     sanity
    0.55
     अनिवार
    0.54
    啦
    0.54
     brilliance
    0.54
    POSITIVE LOGITS
     almost
    1.30
    almost
    1.22
     Almost
    1.20
     거의
    1.13
    Almost
    1.05
     presque
    1.03
     bijna
    1.03
     quase
    1.02
     почти
    0.99
     hampir
    0.96
    Activations Density 0.155%

    No Known Activations