© 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. 10-GEMMASCOPE-RES-131K
    7. 12818
    Prev
    Next
    INDEX
    Explanations

    building relationships and friendships

    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_10/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
     to
    -1.72
     able
    -1.30
     poë
    -1.30
    ↵
    -1.30
    
    -1.27
    ledem
    -1.23
     einiges
    -1.23
    ку
    -1.20
    になっています
    -1.18
    になっている
    -1.15
    POSITIVE LOGITS
     through
    2.16
     where
    1.63
     with
    1.61
     melalui
    1.59
     when
    1.49
    美术
    1.41
    гія
    1.35
    atação
    1.32
     via
    1.32
    phoric
    1.30
    Activations Density 0.027%

    No Known Activations