© 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. 248027
    Prev
    Next
    INDEX
    Explanations

    administration, potato, conflict, gifting

    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
    市内
    0.46
    อยู่
    0.46
    ่น
    0.46
    埆
    0.45
    পন্থী
    0.44
    ﻚ
    0.43
    কদের
    0.43
    ਾਨੂੰ
    0.42
    (",");
    0.42
    ნ
    0.42
    POSITIVE LOGITS
    her
    0.47
    s
    0.47
     endometri
    0.46
     Hez
    0.46
     aut
    0.45
     tenacity
    0.44
     जब
    0.44
    wear
    0.43
     ritual
    0.43
     Liu
    0.42
    Activations Density 0.001%

    No Known Activations