© 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. 28597
    Prev
    Next
    INDEX
    Explanations

    find someone, as incorrect

    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
    sluš
    0.47
    agree
    0.42
    ਇ
    0.42
    personal
    0.41
    historic
    0.41
    perl
    0.40
     erfolgt
    0.40
    at
    0.39
    her
    0.39
     erfolgte
    0.39
    POSITIVE LOGITS
     ব্লগ
    0.48
     অয়েল
    0.48
    来了
    0.43
     Markers
    0.41
    裤
    0.41
    럏
    0.40
     कू
    0.39
    下さい
    0.39
    ണിത്
    0.39
    나
    0.39
    Activations Density 0.023%

    No Known Activations