© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    guaranteed financial outcomes

    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
    ített
    2.92
     اعظم
    2.78
     پنج
    2.76
     मही
    2.62
    ítés
    2.53
    𝖙
    2.53
    ğim
    2.51
     BufferedReader
    2.46
    𝚒
    2.46
    ैनल
    2.43
    POSITIVE LOGITS
    decorate
    2.56
    acuse
    2.53
     hash
    2.39
    繹
    2.37
    oq
    2.30
     hack
    2.30
     condensed
    2.28
    shy
    2.27
    "*
    2.23
     focused
    2.22
    Activations Density 0.125%

    No Known Activations