© 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. 88206
    Prev
    Next
    INDEX
    Explanations

    religious rights

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

    most common

    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
     यकीन
    0.45
     উন্নতির
    0.45
    Triplet
    0.45
    𐰞
    0.43
    Unlocked
    0.43
     আসল
    0.43
     म्हणजेच
    0.42
    Referee
    0.42
     المزيد
    0.42
     оче
    0.41
    POSITIVE LOGITS
     erlaubt
    0.54
     buona
    0.47
    ル
    0.46
     chien
    0.44
     sailboat
    0.43
     courrier
    0.43
     nec
    0.43
     boat
    0.43
     feminina
    0.43
     />;
    0.41
    Activations Density 0.000%

    No Known Activations