© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76637
    Prev
    Next
    INDEX
    Explanations

    names and following words

    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_34/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
     proyek
    -1.12
     diserta
    -1.09
     betrek
    -1.07
     asisten
    -1.05
     minggu
    -1.05
     torba
    -1.02
     parfüm
    -1.02
    displaymath
    -1.01
     tanya
    -1.01
    saia
    -1.00
    POSITIVE LOGITS
     เ
    1.16
     wri
    1.13
     correcto
    1.12
     OMITTED
    1.12
    ఝ
    1.11
    occurs
    1.09
    clearly
    1.09
     propias
    1.09
    operatorname
    1.09
    basically
    1.05
    Activations Density 0.046%

    No Known Activations