© 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. 256217
    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
    t
    0.52
    悦
    0.47
    amard
    0.46
     olma
    0.46
    lük
    0.45
     पाण्याच्या
    0.45
    禀
    0.45
     käytt
    0.45
     فکر
    0.44
     لحاظ
    0.44
    POSITIVE LOGITS
    능
    0.57
     infection
    0.55
     unpopular
    0.54
     Warsaw
    0.54
     Tobago
    0.54
     prepara
    0.54
     athletics
    0.53
     Infection
    0.53
     humidifier
    0.52
     agreement
    0.52
    Activations Density 0.000%

    No Known Activations