© 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. 6509
    Prev
    Next
    INDEX
    Explanations

    out in, we call, over the

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

    planted upside down

    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
    د
    0.60
    م
    0.55
    oucí
    0.51
    י
    0.50
    ف
    0.49
    tolerant
    0.49
    טורק
    0.48
    convert
    0.48
    נ
    0.48
    𝖊
    0.47
    POSITIVE LOGITS
     dân
    0.53
     troupes
    0.49
     flavours
    0.49
     launchers
    0.48
     lysosomes
    0.48
     uds
    0.46
     kết
    0.46
     CHAS
    0.46
     famílias
    0.46
     masks
    0.45
    Activations Density 0.000%

    No Known Activations