© 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. 6377
    Prev
    Next
    INDEX
    Explanations

    or

    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
    𝟬
    0.24
     allong
    0.23
     wszyst
    0.23
    ทั้ง
    0.23
     nejen
    0.23
     tất
    0.22
     także
    0.22
     đây
    0.22
     этих
    0.22
    这两个
    0.22
    POSITIVE LOGITS
    ignal
    0.34
    ients
    0.29
    lege
    0.26
     a
    0.25
    vida
    0.25
    ga
    0.25
    ap
    0.25
     alternatively
    0.23
    agen
    0.23
    atorio
    0.23
    Activations Density 0.500%

    No Known Activations