© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    error message formatting

    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
     ROW
    1.46
     RW
    1.46
    choice
    1.45
     NRP
    1.44
     WALK
    1.40
    耕
    1.39
    NRI
    1.39
    ULATIONS
    1.38
    ONO
    1.37
    selection
    1.36
    POSITIVE LOGITS
     foul
    1.02
    [!
    0.96
     exchangers
    0.95
     behold
    0.94
     laden
    0.94
     critic
    0.93
     chaperone
    0.93
     censor
    0.93
     chaper
    0.90
     chứa
    0.88
    Activations Density 0.052%

    No Known Activations