© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3177
    Prev
    Next
    INDEX
    Explanations

    file paths and directories

    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_7_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
    เขา
    1.97
    +](=
    1.93
    یتے
    1.89
     menek
    1.88
    Nicht
    1.86
    ০
    1.84
    ককে
    1.84
     onge
    1.82
    ย
    1.82
     déprim
    1.81
    POSITIVE LOGITS
    sh
    1.41
     criminal
    1.38
     /
    1.37
     sh
    1.28
     D
    1.28
     Customs
    1.28
     stored
    1.26
     historical
    1.26
     cp
    1.25
    tty
    1.25
    Activations Density 0.029%

    No Known Activations