© 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. 2211
    Prev
    Next
    INDEX
    Explanations

    as far

    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
     offrire
    -1.51
     cambiare
    -1.48
     superare
    -1.44
     imparare
    -1.39
     aiutare
    -1.38
     affrontare
    -1.38
     rimanere
    -1.36
     risolvere
    -1.31
     accedere
    -1.31
     aprire
    -1.31
    POSITIVE LOGITS
     far
    7.88
    far
    5.28
    Far
    4.44
     Far
    3.84
     далеко
    3.83
    FAR
    3.70
     jauh
    3.70
    远
    3.61
     FAR
    3.55
     lejos
    3.22
    Activations Density 0.077%

    No Known Activations