© 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. 243677
    Prev
    Next
    INDEX
    Explanations

    situations ahead, really loving, without discrimination

    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
    peripheral
    0.54
     generative
    0.51
    et
    0.50
     อย่า
    0.47
    resonance
    0.46
     pulverized
    0.45
    4
    0.45
     parallels
    0.45
    MS
    0.44
     peric
    0.44
    POSITIVE LOGITS
     vru
    0.53
     विकलांग
    0.48
    句话
    0.47
    抬头
    0.47
     түз
    0.46
    灵
    0.46
    खिक
    0.46
    ukun
    0.46
    फेर
    0.45
     sáng
    0.45
    Activations Density 0.001%

    No Known Activations