© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6382
    Prev
    Next
    INDEX
    Explanations

    normal

    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
     정의역
    0.39
     മുഴ
    0.38
     божо
    0.38
     jobNumber
    0.38
    ynomial
    0.36
    AndKeys
    0.36
    сель
    0.36
    \/}
    0.36
     গুণ
    0.35
    新区
    0.35
    POSITIVE LOGITS
     P
    0.42
     normal
    0.40
     B
    0.39
     h
    0.38
     D
    0.36
     iron
    0.36
     š
    0.36
    normal
    0.35
     b
    0.34
     pand
    0.34
    Activations Density 0.001%

    No Known Activations