© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75281
    Prev
    Next
    INDEX
    Explanations

    academic affiliations and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necesitaba
    -1.24
    ないけど
    -1.14
    rugu
    -1.09
    ないです
    -1.05
     Sản
    -1.05
    ÊNCIA
    -1.02
     soñ
    -1.01
    ˧
    -1.00
    ugges
    -1.00
     quedarse
    -0.99
    POSITIVE LOGITS
    ensores
    1.05
    tigen
    1.01
    表单
    1.00
    Mű
    0.99
    ✴
    0.98
    elfde
    0.97
    Laporan
    0.95
    Jawaban
    0.94
    orcid
    0.94
    ochond
    0.94
    Activations Density 0.010%

    No Known Activations