© 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-65K
    7. 29853
    Prev
    Next
    INDEX
    Explanations

    Carbonara, pharmacokinetic, achieving

    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_65k_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
    requencies
    0.48
     специально
    0.46
     densities
    0.45
    }}\\
    0.45
    峥
    0.45
     совершенно
    0.44
    awatts
    0.44
     cosas
    0.43
     чему
    0.43
    s
    0.43
    POSITIVE LOGITS
    리
    0.51
    飛行
    0.49
     disrupt
    0.45
    itoti
    0.45
    きる
    0.44
    utilisation
    0.44
    olet
    0.43
     hiko
    0.43
     handbook
    0.43
    olig
    0.43
    Activations Density 0.005%

    No Known Activations