© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13980
    Prev
    Next
    INDEX
    Explanations

    strong negative adjectives/adverbs

    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
     부터
    1.88
     
    1.79
     
    1.76
     변화
    1.75
     युवाओ
    1.74
     !='')
    1.68
     τησ
    1.67
     하였다
    1.67
     )}
    1.65
     אשר
    1.62
    POSITIVE LOGITS
     shitty
    1.81
     fucking
    1.72
     fucked
    1.66
     crappy
    1.62
    fuck
    1.58
     weird
    1.55
     insanely
    1.55
    weird
    1.55
     ridiculously
    1.54
     ridiculous
    1.51
    Activations Density 0.154%

    No Known Activations