© 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. 41-GEMMASCOPE-2-RES-262K
    7. 59849
    Prev
    Next
    INDEX
    Explanations

    moments

    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_all/layer_41_width_262k_l0_big
    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
     ফুল
    0.41
     ਕਰੋ
    0.38
     नेपाली
    0.37
    лово
    0.37
    Borderless
    0.36
     Permanente
    0.36
    烹
    0.36
     ठा
    0.36
     culprits
    0.35
     நெடு
    0.35
    POSITIVE LOGITS
     moments
    0.96
     Moments
    0.89
     moment
    0.79
     Moment
    0.76
     momenti
    0.76
     momentos
    0.73
    moment
    0.65
     momento
    0.63
     момент
    0.57
     момента
    0.57
    Activations Density 0.002%

    No Known Activations