© 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. 260843
    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
    ना
    0.52
     IGN
    0.50
     achar
    0.47
    вина
    0.47
    ה
    0.46
    말
    0.45
    ாட்ட
    0.44
    Speak
    0.44
    소가
    0.44
     उत्सव
    0.44
    POSITIVE LOGITS
     setLayout
    0.44
    äter
    0.41
    ្នាំ
    0.40
    oconvex
    0.40
     ಜನರು
    0.40
    ɹ
    0.40
    layout
    0.40
    pod
    0.40
     Cip
    0.40
    axial
    0.39
    Activations Density 0.000%

    No Known Activations