© 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. 111984
    Prev
    Next
    INDEX
    Explanations

    noun or adjective followed by preposition or conjunction

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

    Japan Rail Pass, imputation, Bolshevik

    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
    icester
    0.42
    岭
    0.42
     كرة
    0.41
     громадян
    0.41
     quốc
    0.41
     говорится
    0.40
    З
    0.39
    累
    0.39
    데일리
    0.39
     itib
    0.38
    POSITIVE LOGITS
    oly
    0.41
     comprehension
    0.41
     tweaking
    0.40
    ded
    0.40
    oum
    0.40
     साथ
    0.39
     shady
    0.39
     automorphisms
    0.39
     Kolmogorov
    0.39
     formdata
    0.39
    Activations Density 0.001%

    No Known Activations