© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154482
    Prev
    Next
    INDEX
    Explanations

    government and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite

    digital interfaces & validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Ked
    0.48
    May
    0.47
    Bradley
    0.45
    पी
    0.45
     люд
    0.45
    Parse
    0.42
    〖
    0.42
    Sterling
    0.42
    Lifetime
    0.41
    Have
    0.41
    POSITIVE LOGITS
     governo
    0.50
    াড়াও
    0.50
     conseils
    0.46
     rivol
    0.46
    在高
    0.45
    波
    0.45
     consejo
    0.45
    rograman
    0.45
    čiti
    0.45
     सरकार
    0.44
    Activations Density 0.000%

    No Known Activations