© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 70
    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
     tarihi
    1.32
    름
    1.31
     gór
    1.29
    ূতন
    1.28
     નજી
    1.25
     tambahan
    1.25
    દા
    1.22
    InstanceState
    1.22
    牛
    1.22
    Ꮫ
    1.21
    POSITIVE LOGITS
    spaced
    1.34
    plotting
    1.31
     opposites
    1.27
    ZIONE
    1.23
    splitting
    1.22
    complement
    1.21
    itat
    1.20
    nation
    1.19
    sided
    1.19
    otechnical
    1.19
    Activations Density 4.796%

    No Known Activations