© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6491
    Prev
    Next
    INDEX
    Explanations

    here are some alternative

    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
    ameen
    1.21
     최종
    1.13
    ioen
    1.01
    淨
    1.00
     revamped
    0.99
     совершен
    0.99
     চূড়ান্ত
    0.97
     vá
    0.93
     કે
    0.93
    岚
    0.93
    POSITIVE LOGITS
     usual
    1.78
     typical
    1.61
     normal
    1.50
    normal
    1.40
    typical
    1.40
     normale
    1.40
    Typical
    1.39
     Usual
    1.36
     customary
    1.33
    Normal
    1.31
    Activations Density 0.384%

    No Known Activations