© 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. 47552
    Prev
    Next
    INDEX
    Explanations

    Tacitus, automated construction, ancient tradition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    0.48
    Penn
    0.45
    čne
    0.44
    חת
    0.43
    Country
    0.43
    Similarity
    0.42
    Engagement
    0.42
    Journal
    0.41
    частли
    0.41
    ೧
    0.41
    POSITIVE LOGITS
     е
    0.48
     tablets
    0.45
     р
    0.45
     கரு
    0.44
     কৌশল
    0.44
     obt
    0.44
     Vader
    0.44
     handyman
    0.43
     ଯ
    0.43
     drastically
    0.43
    Activations Density 0.005%

    No Known Activations