© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 832
    Prev
    Next
    INDEX
    Explanations

    scientific roles

    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
    াদ
    2.36
     carrying
    2.29
     moeda
    2.26
     Carrying
    2.20
    ”(
    2.15
    𝚄
    2.13
    𝒊
    2.08
    𝓵
    2.07
    ษัท
    2.04
    σεις
    2.02
    POSITIVE LOGITS
    ppe
    2.37
    nast
    2.29
    সম্মত
    2.28
     neka
    2.23
    uose
    2.20
     সম্মত
    2.08
    savvy
    2.05
     shad
    1.99
     spus
    1.98
    нду
    1.97
    Activations Density 0.645%

    No Known Activations