© 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. 10-GEMMASCOPE-RES-131K
    7. 205
    Prev
    Next
    INDEX
    Explanations

    file paths and urls

    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
    also
    -1.84
     IBOutlet
    -1.73
    大战
    -1.71
    ranslated
    -1.66
    Also
    -1.60
    いえば
    -1.58
    谕
    -1.53
     also
    -1.51
     myös
    -1.48
    ])),
    -1.46
    POSITIVE LOGITS
     we
    1.85
    !
    1.47
     of
    1.46
    kredit
    1.41
     ถ้า
    1.38
     it
    1.38
    postolic
    1.36
     Banyak
    1.34
     yüzden
    1.31
     whoſe
    1.31
    Activations Density 0.061%

    No Known Activations