© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4226
    Prev
    Next
    INDEX
    Explanations

    but I'll start with

    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
    雖
    0.43
    Although
    0.41
     although
    0.40
    although
    0.38
     despite
    0.38
    虽
    0.38
     Although
    0.34
    တယ်။
    0.33
    但在
    0.33
     Despite
    0.33
    POSITIVE LOGITS
    staande
    0.36
    왕
    0.35
     लगाएं
    0.35
     (!)
    0.34
     공연
    0.34
     차
    0.34
     heiß
    0.34
    保险
    0.34
     oplossing
    0.34
    ؎
    0.34
    Activations Density 0.170%

    No Known Activations