© 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. 34-GEMMASCOPE-RES-131K
    7. 6761
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and licensing text

    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
     or
    -0.97
    !
    -0.95
    !!!!
    -0.93
    ир
    -0.93
    ที่จะ
    -0.91
     ,
    -0.90
    !!!
    -0.88
    dieta
    -0.87
     to
    -0.85
    !!
    -0.85
    POSITIVE LOGITS
     conoscere
    1.10
     cappuccio
    1.09
     redou
    1.08
    Zdrav
    1.07
     avevo
    1.05
     hébergement
    1.05
     scatola
    1.05
     situazioni
    1.05
     dismant
    1.04
     aiuto
    1.04
    Activations Density 0.001%

    No Known Activations