© 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. 6162
    Prev
    Next
    INDEX
    Explanations

    news topics

    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
    蒾
    2.70
    ्त
    2.46
    tter
    2.42
    𝐥
    2.36
    বাই
    2.24
    ldquo
    2.20
     ď
    2.20
    rison
    2.15
    utional
    2.13
     manners
    2.13
    POSITIVE LOGITS
    ுகள்
    2.96
    ет
    2.74
    ется
    2.66
    𝒾
    2.53
    той
    2.50
    ету
    2.41
    𝚊
    2.37
    óstico
    2.37
    isotropic
    2.35
    ुक
    2.34
    Activations Density 0.061%

    No Known Activations