© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4090
    Prev
    Next
    INDEX
    Explanations

    fill in the blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ​—
    1.98
    其中包括
    1.65
    częściej
    1.62
    ，“
    1.58
     –,
    1.58
    、“
    1.58
    <unused342>
    1.58
     —,
    1.52
    与此同时
    1.51
     omfatt
    1.51
    POSITIVE LOGITS
     fucking
    2.49
     shit
    2.05
     lol
    2.01
     crap
    1.99
     kinda
    1.98
     bullshit
    1.98
     sooo
    1.95
    걍
    1.95
     soooo
    1.93
     ppl
    1.89
    Activations Density 0.118%

    No Known Activations