© 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. 12011
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    线路
    1.75
    BusinessType
    1.63
     funcionalidades
    1.61
     dimensioni
    1.60
     filosofia
    1.54
     strutture
    1.52
     habitaciones
    1.51
    *************
    1.51
    所在地
    1.49
    миз
    1.49
    POSITIVE LOGITS
     Armour
    1.34
     shear
    1.31
    ARCH
    1.29
    ற்றம்
    1.28
    셉
    1.27
    eah
    1.26
     ervoor
    1.25
    sberg
    1.24
    orch
    1.24
     chance
    1.24
    Activations Density 0.154%

    No Known Activations