© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    💯 emoji usage

    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
    4
    0.44
    6
    0.44
    0
    0.43
    5
    0.43
    2
    0.42
    3
    0.40
    0.38
    9
    0.37
    8
    0.36
    E
    0.35
    POSITIVE LOGITS
    嵬
    0.29
     bullies
    0.28
    надцать
    0.28
    阏
    0.27
    蟀
    0.27
    ังหวัด
    0.26
     젊
    0.26
    🤥
    0.26
     clergyman
    0.26
    덟
    0.26
    Activations Density 0.043%

    No Known Activations