© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11989
    Prev
    Next
    INDEX
    Explanations

    months and days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    겟
    0.42
    किया
    0.41
     calibrate
    0.38
    äft
    0.37
     সঙ্গী
    0.37
    álie
    0.37
     veins
    0.36
    emps
    0.36
     planes
    0.35
     inserts
    0.35
    POSITIVE LOGITS
     adalah
    0.49
    =[],
    0.49
     là
    0.47
     Boltzmann
    0.41
     Caj
    0.41
     violência
    0.40
    =[]
    0.40
     Là
    0.39
    ພວກເຮົາ
    0.39
    में
    0.38
    Activations Density 0.001%

    No Known Activations