© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67103
    Prev
    Next
    INDEX
    Explanations

    plus, if

    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
     in
    -2.69
    ⇰
    -2.25
     Because
    -2.06
    t
    -2.05
     after
    -1.89
     pushing
    -1.88
     plethora
    -1.87
    )$
    -1.84
     mainly
    -1.84
     mostly
    -1.84
    POSITIVE LOGITS
    ⌵
    1.98
    其他的
    1.94
    ,
    1.92
    菒
    1.91
     vê
    1.91
     XVI
    1.89
    ୬
    1.88
    苤
    1.87
    鵙
    1.87
    戋
    1.86
    Activations Density 0.005%

    No Known Activations