© 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. 41955
    Prev
    Next
    INDEX
    Explanations

    biblical visions, Cornelius, election

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

    but secretly

    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
     今
    0.56
     বাসন
    0.52
    ュー
    0.50
    ان
    0.48
     未
    0.48
    डीएम
    0.47
    ח
    0.47
    வைக்
    0.46
    𝕨
    0.46
    বড়
    0.46
    POSITIVE LOGITS
     Melo
    0.43
     Depend
    0.41
     eco
    0.40
     Cull
    0.40
     Ont
    0.38
     сви
    0.38
     российской
    0.38
     Ub
    0.38
     Alternatively
    0.37
     Servi
    0.37
    Activations Density 0.000%

    No Known Activations