© 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. 195846
    Prev
    Next
    INDEX
    Explanations

    tulip dining

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

    describes suppressed knowledge

    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
    माजिक
    0.55
     можуть
    0.48
    ്‍
    0.45
     шко
    0.45
     wymien
    0.44
    hotite
    0.44
     povas
    0.44
     twierd
    0.43
    者は
    0.43
     mohou
    0.43
    POSITIVE LOGITS
    imar
    0.51
    ou
    0.49
    ok
    0.49
    。
    0.49
    ↵
    0.48
     of
    0.48
    leton
    0.48
    en
    0.47
    يس
    0.47
    findViewById
    0.47
    Activations Density 0.000%

    No Known Activations