© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161662
    Prev
    Next
    INDEX
    Explanations

    city centre

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

    bullish and bearish divergences

    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
     வட்ட
    0.51
     ঘন্টার
    0.47
     eventful
    0.46
    の内
    0.45
     ঘণ্টার
    0.43
     buts
    0.43
     k
    0.42
     foram
    0.41
    ,
    0.41
     Checked
    0.40
    POSITIVE LOGITS
    इट
    0.57
    𒉈
    0.51
    ین
    0.49
    INDE
    0.49
    लु
    0.48
    DWARF
    0.47
    劷
    0.47
     idées
    0.46
    ו
    0.46
    સી
    0.45
    Activations Density 0.000%

    No Known Activations