© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 223234
    Prev
    Next
    INDEX
    Explanations

    reporting and search

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

    where wires and cables

    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
     ง่าย
    0.52
     উপায়
    0.49
     ยาก
    0.48
     можуть
    0.47
     黃
    0.47
     compacto
    0.47
     ನೇ
    0.46
    锐
    0.46
    ామ
    0.46
     簡単
    0.45
    POSITIVE LOGITS
     Pence
    0.48
     compte
    0.47
    риди
    0.45
     Commodities
    0.45
     अँ
    0.45
    did
    0.42
     Ode
    0.42
     DMD
    0.42
     dese
    0.42
    降
    0.42
    Activations Density 0.000%

    No Known Activations