© 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. 22-GEMMASCOPE-RES-131K
    7. 33474
    Prev
    Next
    INDEX
    Explanations

    evaluated, tested, studied, assessed

    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_22/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
    منة
    -0.94
    意思是
    -0.91
     possibly
    -0.89
     STILL
    -0.85
     or
    -0.85
     probably
    -0.84
     might
    -0.83
    di
    -0.82
     that
    -0.82
     Served
    -0.81
    POSITIVE LOGITS
     against
    1.20
     التطبيق
    1.02
     myös
    1.02
    jbl
    1.01
     with
    1.00
    ⁼
    1.00
     on
    0.99
    inação
    0.98
     TIEMPO
    0.98
     konkrét
    0.97
    Activations Density 0.136%

    No Known Activations