© 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. 26570
    Prev
    Next
    INDEX
    Explanations

    authentic western heritage

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

    photograph, frame, root, however, angry

    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
     სან
    0.47
    excluding
    0.47
     블루
    0.46
    मलव
    0.46
     даты
    0.45
    아
    0.45
     ਹ
    0.45
    쫌
    0.44
    ブルー
    0.44
    Gosudarstvennyj
    0.44
    POSITIVE LOGITS
     blog
    0.47
    били
    0.44
     ер
    0.41
     trest
    0.41
     egensk
    0.40
     mine
    0.39
     blogging
    0.38
     somit
    0.38
     ground
    0.38
     Blog
    0.38
    Activations Density 0.000%

    No Known Activations