© 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. 5334
    Prev
    Next
    INDEX
    Explanations

    people and groups

    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
    commonly
    0.53
     osoba
    0.52
     quelquefois
    0.51
     erforderlich
    0.51
     sól
    0.50
    %)$
    0.50
     ล
    0.49
    ើន
    0.49
     assays
    0.49
     improperly
    0.48
    POSITIVE LOGITS
     themselves
    0.80
    들에게
    0.78
    들이
    0.74
    들의
    0.68
    들은
    0.66
    们的
    0.64
    들
    0.63
     الذين
    0.59
    ların
    0.58
    们
    0.57
    Activations Density 0.006%

    No Known Activations