© 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. 20584
    Prev
    Next
    INDEX
    Explanations

    conditional or subsequent phrase

    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
    पर्यंत
    0.46
     conseil
    0.44
    encerramento
    0.41
    썼
    0.41
    সুর
    0.40
    ിയ്
    0.40
    کریاں
    0.39
    пети
    0.39
    পাশে
    0.39
    高い
    0.39
    POSITIVE LOGITS
     ताजा
    0.57
     aston
    0.52
     精
    0.51
     digging
    0.48
     ఎ
    0.47
     গান্ধী
    0.47
     كت
    0.47
    riek
    0.46
     jd
    0.46
     infrac
    0.45
    Activations Density 0.001%

    No Known Activations