© 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. 11772
    Prev
    Next
    INDEX
    Explanations

    what is being enjoyed

    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
     usual
    -1.25
     you
    -1.23
    S
    -1.19
     cualquier
    -1.13
     desirable
    -1.11
     учета
    -1.09
    匆匆
    -1.05
     источники
    -1.05
     It
    -1.05
    țională
    -1.05
    POSITIVE LOGITS
    ably
    1.75
     watching
    1.57
     being
    1.44
     the
    1.34
    watching
    1.32
     themselves
    1.27
     vertes
    1.25
    мым
    1.18
     quartiers
    1.17
    芣
    1.16
    Activations Density 0.012%

    No Known Activations