© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9140
    Prev
    Next
    INDEX
    Explanations

    about others

    np_acts-logits-general · gemini-2.5-flash-lite

    are concerned or struggling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nejen
    0.47
     和
    0.39
     
    0.37
     hoặc
    0.35
     ovaries
    0.35
     pliers
    0.34
     很
    0.33
    ")
    0.32
     alebo
    0.32
     quieras
    0.31
    POSITIVE LOGITS
     также
    0.42
     других
    0.41
     другими
    0.41
     म्हणून
    0.40
    อื่นๆ
    0.40
     અન્ય
    0.38
     інших
    0.38
    າມາດ
    0.38
     अन्य
    0.38
     दूसरों
    0.38
    Activations Density 0.282%

    No Known Activations