© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2559
    Prev
    Next
    INDEX
    Explanations

    GPT, OpenAI, language models

    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_40_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
    🫶
    1.13
    🥹
    1.05
    🫰
    1.05
    🫠
    1.00
    🩷
    0.98
    🫡
    0.97
    🫣
    0.96
    🫢
    0.93
    🩶
    0.91
    🫤
    0.88
    POSITIVE LOGITS
     coronavirus
    0.86
     ২০১৯
    0.78
     Coronavirus
    0.70
     Trump
    0.68
    Coronavirus
    0.59
    Trump
    0.56
     pre
    0.54
     করোনাভাই
    0.54
    coronavirus
    0.54
     ২০১৮
    0.50
    Activations Density 0.036%

    No Known Activations