© 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. 260888
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ேத்க
    0.44
    மன்ற
    0.44
     фено
    0.44
    తో
    0.43
    warts
    0.43
     ключе
    0.42
    メータ
    0.42
    令
    0.42
    itiv
    0.40
    跹
    0.40
    POSITIVE LOGITS
     barring
    0.50
    sponsored
    0.47
     penj
    0.46
     karyawan
    0.46
    cD
    0.46
    銷
    0.46
     ਸੀ
    0.46
     dė
    0.46
    sca
    0.45
     Güney
    0.45
    Activations Density 0.001%

    No Known Activations