© 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. 13-GEMMASCOPE-2-RES-16K
    7. 802
    Prev
    Next
    INDEX
    Explanations

    you provide

    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_13_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
    юще
    2.00
    ᵃ
    1.89
    🫠
    1.89
     яко
    1.88
    പ്പുറ
    1.87
    occhio
    1.84
    Perspective
    1.83
    ㈠
    1.82
     Perspective
    1.81
    Ed
    1.81
    POSITIVE LOGITS
     pouvez
    2.78
     devez
    2.44
     yourself
    2.31
     serez
    2.29
     savez
    2.27
     devrez
    2.26
     будете
    2.25
     можете
    2.24
     kunt
    2.24
    ebilirsiniz
    2.18
    Activations Density 2.414%

    No Known Activations