© 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. 64200
    Prev
    Next
    INDEX
    Explanations

    bedroom

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

    used in standards

    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
    ו
    0.48
     medica
    0.44
     mediated
    0.41
     obstetric
    0.41
    disabled
    0.41
     mediating
    0.41
     bipartite
    0.39
     _|
    0.38
    痛
    0.37
     законом
    0.37
    POSITIVE LOGITS
     음악
    0.61
     музи
    0.54
    тори
    0.53
     प्रचंड
    0.50
     앞
    0.48
     muziek
    0.48
    锃
    0.47
     เห็น
    0.47
     absen
    0.47
    演绎
    0.47
    Activations Density 0.000%

    No Known Activations