© 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. 41-GEMMASCOPE-2-RES-262K
    7. 4224
    Prev
    Next
    INDEX
    Explanations

    "know that" or direct speech

    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_all/layer_41_width_262k_l0_big
    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
    យៈ
    0.29
    ร้อม
    0.28
    ূল
    0.28
    ามารถ
    0.27
     அள
    0.26
    繁忙時間服務
    0.26
    ្នុង
    0.25
    <unused671>
    0.25
     equaling
    0.25
    رځ
    0.25
    POSITIVE LOGITS
     bahwa
    0.31
     أنه
    0.27
     that
    0.26
     Nietzsche
    0.25
     Nobel
    0.24
     Mahatma
    0.24
     Museum
    0.24
     she
    0.24
     ότι
    0.24
     Fark
    0.24
    Activations Density 0.005%

    No Known Activations