© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63130
    Prev
    Next
    INDEX
    Explanations

    Replace f(x) with y

    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
    ѫ
    0.42
    构建
    0.40
    ǐ
    0.40
    *>
    0.40
    
    0.40
    
    0.40
    通
    0.39
    釆
    0.39
    iót
    0.38
    *}$
    0.38
    POSITIVE LOGITS
    産の
    0.46
     Ais
    0.44
     toujours
    0.42
     verre
    0.42
     windfall
    0.42
    देवी
    0.42
    wner
    0.42
     GaAs
    0.42
     entusias
    0.41
    நிதி
    0.41
    Activations Density 0.002%

    No Known Activations