© 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-262K
    7. 40407
    Prev
    Next
    INDEX
    Explanations

    mundane lifted

    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
    ту
    0.47
    Ти
    0.41
    तू
    0.40
    ѕ
    0.39
    밌
    0.39
    owanie
    0.39
     abit
    0.39
    कोई
    0.39
    ԝ
    0.39
    azing
    0.38
    POSITIVE LOGITS
     supermerc
    0.51
    gruntled
    0.49
     Meghan
    0.49
     cuja
    0.49
     Soho
    0.46
     fêtes
    0.45
     oligonucleotide
    0.45
     headquartered
    0.44
     fête
    0.44
     dî
    0.44
    Activations Density 0.002%

    No Known Activations