© 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. 225511
    Prev
    Next
    INDEX
    Explanations

    words after specific words

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

    unconventional superconductors

    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
    ﺧ
    0.49
    נ
    0.48
    י
    0.47
    ש
    0.47
     অনুম
    0.46
    ר
    0.46
    破損
    0.46
     APPROVED
    0.46
    𝘂
    0.46
    硯
    0.45
    POSITIVE LOGITS
    heh
    0.46
     były
    0.44
     echt
    0.44
     gäller
    0.44
    Yes
    0.43
     театра
    0.43
     जानते
    0.43
     intéressant
    0.42
     представлены
    0.42
     [+
    0.41
    Activations Density 0.001%

    No Known Activations