© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2926
    Prev
    Next
    INDEX
    Explanations

    markup/code syntax

    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
     now
    -2.02
    Now
    -1.36
     теперь
    -1.30
     maintenant
    -1.27
     ahora
    -1.24
     artık
    -1.18
     Ahora
    -1.17
    now
    -1.15
     désormais
    -1.13
     अब
    -1.12
    POSITIVE LOGITS
     who
    1.42
     again
    1.30
     than
    1.16
     then
    1.15
     Again
    1.13
    仍然
    1.09
    Again
    1.05
     vẫn
    1.02
     souvent
    1.02
     снова
    1.02
    Activations Density 0.010%

    No Known Activations