© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59002
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    Utiliz
    -1.24
     utilized
    -1.23
     أيضًا
    -1.12
     Utilizing
    -1.11
     Utilize
    -1.11
     impacted
    -1.11
    utilized
    -1.10
     również
    -1.09
     basé
    -1.07
     realmente
    -1.06
    POSITIVE LOGITS
     reckoned
    1.16
     empezó
    1.15
    ėjimo
    1.09
     plainly
    1.09
     learnt
    1.09
     ought
    1.09
    óri
    1.07
     reckon
    1.03
     partly
    1.00
    issaient
    1.00
    Activations Density 0.007%

    No Known Activations