© 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. 252790
    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
    身
    0.45
    வும்
    0.44
     thờ
    0.42
    at
    0.41
     cree
    0.41
     deity
    0.41
    Historical
    0.41
    教
    0.40
    ्युनिटी
    0.40
    యు
    0.40
    POSITIVE LOGITS
     começando
    0.50
     muszą
    0.48
     começa
    0.48
     begint
    0.47
     cominc
    0.46
     invoicing
    0.46
     hemispheres
    0.46
     lasts
    0.44
    erler
    0.44
     поха
    0.43
    Activations Density 0.010%

    No Known Activations