© 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. 26395
    Prev
    Next
    INDEX
    Explanations

    hand gestures and pointing

    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
      
    -1.41
    ↵↵↵
    -1.19
    -1.18
    ↵
    -1.12
    ↵↵
    -1.05
     ausdrück
    -1.02
    在这里
    -1.02
    Rationale
    -1.01
     In
    -0.98
    这种
    -0.97
    POSITIVE LOGITS
    佧
    1.43
    ྃ
    1.30
     colombiano
    1.27
     akrab
    1.27
     sapat
    1.26
     confirmó
    1.23
    示意
    1.21
    婓
    1.20
    隳
    1.20
    árbol
    1.19
    Activations Density 0.007%
    No Known Activations