© 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. 108599
    Prev
    Next
    INDEX
    Explanations

    percentages or counts following parentheses

    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
     so
    -1.43
     instead
    -1.04
     that
    -1.02
     вместо
    -1.02
    ]))
    -1.00
     all
    -1.00
     themselves
    -0.98
     again
    -0.94
     when
    -0.94
     people
    -0.94
    POSITIVE LOGITS
     mystérie
    1.06
    Jumlah
    1.05
    openqa
    1.05
    Antworten
    1.05
    sprecher
    1.04
    recently
    1.02
    Chất
    1.02
    செ
    1.01
    ftet
    1.00
    کفش
    1.00
    Activations Density 0.021%

    No Known Activations