© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12719
    Prev
    Next
    INDEX
    Explanations

    requests for an outline

    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
    ्रे
    2.80
    ਵਾਈ
    2.64
    ೋ
    2.60
    osim
    2.59
    াকের
    2.56
    ভেজ
    2.54
    क्की
    2.53
    दायी
    2.53
    償
    2.53
    ्री
    2.49
    POSITIVE LOGITS
    iota
    2.31
    𝙘
    2.29
    aky
    2.25
    InputBorder
    2.22
    cmds
    2.09
    muir
    2.07
    म्मीद
    2.07
    groovy
    2.04
    serde
    2.02
     ہوئے
    2.01
    Activations Density 0.028%

    No Known Activations