© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227336
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.52
     胸
    0.50
    ନ
    0.47
    checkBox
    0.45
     expediente
    0.45
     vín
    0.45
     unlink
    0.45
    bpm
    0.45
     институт
    0.44
    饉
    0.44
    POSITIVE LOGITS
    </h3>
    0.47
    0.43
    </strong>
    0.42
    allows
    0.41
    ikut
    0.38
     Banks
    0.37
    its
    0.37
    </h5>
    0.36
    Banks
    0.36
     Floral
    0.35
    Activations Density 0.011%

    No Known Activations