© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6170
    Prev
    Next
    INDEX
    Explanations

    asterisk, sorry, jack, Eminem

    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
    と呼ばれる
    1.01
     themselves
    0.91
     XNUMX
    0.90
    ียม
    0.89
     enteros
    0.88
    -
    0.87
     integral
    0.85
    ‑
    0.85
     denials
    0.84
    を用
    0.82
    POSITIVE LOGITS
    yeah
    1.62
     kinda
    1.53
    reciate
    1.50
    wonderful
    1.48
     hehe
    1.45
     근데
    1.42
    amazing
    1.40
    appreci
    1.40
    lovely
    1.40
     ㅎㅎ
    1.36
    Activations Density 0.241%

    No Known Activations