© 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. 135825
    Prev
    Next
    INDEX
    Explanations

    buying/hiring themes

    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
    ட்டு
    0.48
    ིག་
    0.47
    Ғ
    0.47
    }\,
    0.42
    Թ
    0.41
    སྐ
    0.41
    མ་
    0.41
     embarrass
    0.40
    輒
    0.40
    cy
    0.40
    POSITIVE LOGITS
    štu
    0.47
     kjø
    0.45
     obtenu
    0.45
     acheter
    0.44
     شراء
    0.44
    oleč
    0.43
     hired
    0.43
     покуп
    0.43
     verk
    0.43
     保
    0.43
    Activations Density 0.005%

    No Known Activations