© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101582
    Prev
    Next
    INDEX
    Explanations

    take shortcuts

    np_acts-logits-general · gemini-2.5-flash-lite

    irony, unexpected, health insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    נה
    0.54
    4
    0.50
    цию
    0.50
     eğer
    0.48
    nın
    0.47
    MENT
    0.47
    ми
    0.47
    EMENT
    0.47
    6
    0.46
    CAR
    0.46
    POSITIVE LOGITS
     porcine
    0.45
     Fulbright
    0.45
     Deadly
    0.44
    ('').
    0.44
     Snack
    0.44
     Pulmonary
    0.43
     Pediatric
    0.42
     Pharisees
    0.42
     Glut
    0.42
     விஞ்ஞான
    0.41
    Activations Density 0.000%

    No Known Activations