© 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. 83853
    Prev
    Next
    INDEX
    Explanations

    states that are not working

    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
     Rodeo
    0.46
    скай
    0.45
     Broker
    0.43
     thoughtfulness
    0.43
     решил
    0.42
     LDAP
    0.42
     long
    0.41
    郊
    0.41
     وار
    0.41
     sabbatical
    0.41
    POSITIVE LOGITS
     ngôn
    0.50
    ellington
    0.48
     tên
    0.48
     extinguished
    0.47
     utterances
    0.46
    OnUiThread
    0.46
     énon
    0.45
     chưa
    0.44
     flushed
    0.44
    tanh
    0.43
    Activations Density 0.004%

    No Known Activations