© 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. 22-GEMMASCOPE-RES-131K
    7. 129542
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

    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
     najbol
    -0.98
    GOTREF
    -0.94
    ₾
    -0.90
    ikti
    -0.88
    ("")]
    -0.86
    UCHAR
    -0.86
    laration
    -0.85
     musisz
    -0.84
    inander
    -0.84
    ϋ
    -0.83
    POSITIVE LOGITS
     using
    0.94
     rather
    0.88
     instead
    0.86
     arba
    0.85
    //
    0.85
    interess
    0.81
     bukan
    0.81
    entukan
    0.79
     formerly
    0.79
     new
    0.76
    Activations Density 0.016%

    No Known Activations