© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13437
    Prev
    Next
    INDEX
    Explanations

    hypothetical statements with "if" or "like"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     nahil
    1.60
    潴
    1.52
     samoglas
    1.43
     乀
    1.40
     함수의
    1.40
     сосре
    1.40
     dilwale
    1.39
     淡
    1.39
     하지
    1.38
     思い
    1.38
    POSITIVE LOGITS
    information
    1.01
    um
    0.93
    invest
    0.92
    and
    0.90
    lung
    0.89
     information
    0.89
    uniform
    0.89
    ist
    0.88
    ism
    0.88
    either
    0.87
    Activations Density 0.005%

    No Known Activations