© 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. 101788
    Prev
    Next
    INDEX
    Explanations

    wisdom teeth

    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
     محاس
    0.40
     hologram
    0.38
    䜌
    0.38
     kalk
    0.38
     Collin
    0.37
     mek
    0.35
     maid
    0.35
     meal
    0.35
     maids
    0.35
     challenge
    0.34
    POSITIVE LOGITS
    Current
    0.48
     Updates
    0.44
    Те
    0.43
    Ка
    0.42
    Мы
    0.42
    Ч
    0.41
    ὠ
    0.41
    Λ
    0.41
    MTAB
    0.40
     Current
    0.40
    Activations Density 0.086%

    No Known Activations