© 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. 27239
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and protocols

    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
    </em>
    -2.72
    0
    -2.42
    A
    -2.41
    It
    -2.33
     For
    -2.28
     Depending
    -2.27
     Both
    -2.22
     At
    -2.19
     If
    -2.16
    5
    -2.14
    POSITIVE LOGITS
    犼
    2.56
    趿
    2.16
    踯
    2.13
    
    2.09
    蹰
    2.08
     visualización
    2.05
    
    2.05
     instalación
    2.05
     verschillende
    1.98
    呖
    1.98
    Activations Density 0.100%

    No Known Activations